Intel 情报源

Claude Fable 5.1 and Claude Mythos 5.1

Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation

LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the internal procedure by which they assign a rating remains poorly understood. We investigate this procedure mechanistically through an eight-attack perturbation taxonomy across the Readability and Adequacy dimensions of NLG quality, a generation pipeline that produces paired clean and corrupt summaries with controlled error intensity and explicit token-level modification maps, and a four-experiment battery of causal tracing, logit-lens vocabulary projection, and attention-head knockout applied to Themis (Llama-3-8B) and Prometheus (Mistral-7B). Both evaluators implement a structured, coherent evaluation pipeline operating in two stages: below layer 15, attention performs local error comparison and routes the result to the final input position; above it, the MLP cascade integrates the signal and writes the rating, with the decision crystallizing in the residual stream at a sharp late layer (L = 26 on Themis, L = 25 on Prometheus). Furthermore, a base-model control at the same scale (Llama-3-8B) reproduces the routing architecture and crystallization but not the stage separation, isolating the two mechanisms that fine-tuning specifically installs, suppression of below-L15 MLP contribution at the last position and a two-layer advance of the crystallization depth, indicating that fine-tuning sculpts an existing substrate rather than building the pipeline from scratch. We release the source code and data at https://github.com/himil-v/judge-mech

Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We propose PTA-IRT, a Privileged Trajectory-Aware Item Response Theory framework that fuses process and outcome signals. Historical execution trajectories supply process-level evidence beyond pass/fail, such as explored context, attempted edits, and solving paths, which PTA-IRT uses as privileged information for calibration subset selection and ability estimation. Under low calibration budgets, PTA-IRT consistently outperforms prior IRT baselines on score and ranking recovery across four SWE benchmarks. Code and data are publicly available at https://github.com/DeepSoftwareAnalytics/PTA-IRT.

Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods typically provide context as task-level support, without explicitly identifying the critical tokens that require fine-grained repository context during generation. During the autoregressive generation process of LLMs, errors often concentrate at a small number of decisive positions: once such tokens are generated incorrectly, subsequent code may follow an incorrect semantic path and eventually lead to functional failure. We refer to these positions as "critical tokens". In this paper, we propose ACToR, an adaptive critical token-aware retrieval framework for repository-level code generation. ACToR identifies critical tokens during generation and triggers targeted retrieval on demand to provide repository context at these decisive positions. In addition, we design a position-aware weighting method for dense retrievers to prioritize context that is more informative for generation. We evaluate ACToR on two representative repository-level benchmarks, RepoExec and CoderEval. Experimental results show that ACToR consistently outperforms state-of-the-art methods, achieving relative improvements of 8.4% on RepoExec and 15.4% on CoderEval. Beyond performance gains, we systematically quantify the impact of critical tokens, revealing their central role in major generation failures and highlighting the necessity of targeted retrieval strategies. We provide the code and data at https://github.com/DeepSoftwareAnalytics/ACToR.

CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?

Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate through dependencies and cleanup. We introduce CordisBench, a 1,200-question benchmark of this lifecycle reasoning. It combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencies and cleanup, and asks models to identify affected components, predict state after a specified teardown order, determine which conditions hold under all or some orders, and choose reconfigurations that succeed when executed. Across these tasks, we evaluate three efficiency-oriented models at low reasoning effort with 2, 4, 8, 16, 24, or 32 relevant interactions, using deterministic task-specific scoring. Models usually handle small systems well but grow less reliable as more interactions become relevant, especially when predicting final state and when reasoning across teardown orders. Additional inference effort recovers marked gains for some models. The cost is nontrivial: on our 16-interaction subset, GPT-5.6 Luna uses nearly 3,000 reasoning tokens per question at medium effort. For these controlled instances, that cost is avoidable: an independent finite reference semantics agrees with Cordis execution on every observation and action outcome used for scoring across all 528 executable questions.

The Rise of Verbal Reinforcement Learning

Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent, preferences, and causal structure in forms interpretable by both humans and modern language models. We call this paradigm Verbal Reinforcement Learning (VRL) and offer the first unified account of it. We organize the field around a single axis, \textit{when} verbal feedback takes effect in an agent's lifecycle and \textit{what} it modifies, yielding three pillars: (1) \textbf{Language as Grounding Signal}, where language defines the task itself by specifying goals, states, and reward structures; (2) \textbf{Language as Deliberative Feedback}, where natural language guides reasoning at test time without the need to update model parameters; (3) \textbf{Language as Learning Signal}, where language-based feedback shapes model parameters through training. Within each pillar, we synthesize representative work, distinguish key subcategories of approaches, and outline the distinct role language plays in shaping agent behavior. Together, this taxonomy shows how verbal reinforcement is reshaping agent development, while also defining the challenges and opportunities for building more capable and aligned agents.

Mechanism Design for Alignment and Control

We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabilities (feasible actions and information) are unknown. We want such agents to act on our behalf so mechanisms must incentivize both honesty and obedience. A one-sided imitation structure---capabilities can be concealed but not counterfeited---yields a revelation principle, a characterization of implementable policies via nested cyclical monotonicity, and conditions under which eliciting higher-order beliefs can discipline multiple agents. We apply our framework to stylized examples of (i) sandbagging in which a more capable agent pretends to be less capable; (ii) an alignment--interpretability trade-off, where the two are substitutes in the instrument but complements in value; (iii) discipline via peer scoring; (iv) coupling rewards to induce competition among multiple agents; and (v) scalable oversight and reward shaping.

StudentSim: Training LLM-based Student Simulators

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-language English writing, and mathematics, using public learner datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.

Designing Proactive Thought Partners for Writing

Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time, yet existing proactive tools largely focus on generic textual assistance, such as autocomplete. This paper studies the design space of proactive thought partners: AI agents that proactively offer customizable, higher-level cognitive support during writing. We instantiated this concept in a technology probe and deployed it with 16 participants for one week. The probe allows users to create partners by configuring their roles and proactivity. As users write, relevant partners take the initiative at appropriate moments to offer suggestions. Our findings show that participants configured proactive support through prospective planning, used suggestions for both idea generation and self-monitoring, and valued lightweight visual representations alongside non-directive rhetorical framing for non-intrusive interventions. We derive implications for designing proactive writing assistants around customization, timing, engagement, and representation.

Claude Fable 5.1 and Claude Mythos 5.1

The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally

Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground truth (raise each layer to 8-bit in turn and measure the accuracy it recovers) across 9 open-weight models in 4 architecture families, we test 3 intuitive hypotheses: that quantization damage lives in task circuits, where the model computes, or in weight statistics. None of them predicts which layers benefit from restored precision. Recovery is instead diffuse: for 8 of 9 models, recovering 75% of the gap takes roughly half the layers; the lone exception, Qwen3-8B, is sharply concentrated. At a matched precision budget, spending it globally on finer quantization granularity beats locally repairing the most recoverable layers for all 8 group-128-compatible models (all but OpenLLaMA, whose width rules out group-128), by 21-52 points, including the concentrated Qwen3-8B. We report 2 secondary findings: the residual is budget-limited (8-bit is near-lossless in our evaluation across RTN, GPTQ, and AWQ), and the location of peak recovery correlates with architecture within a family, though not across families. Within this budget setting, global granularity is a better default than selectively protecting critical layers. More broadly, cheap signals that correlate with quantization damage do not necessarily identify where restoring precision improves accuracy; this must be tested with causal intervention.

The creator of Jujutsu has joined ERSC

Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics

Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a fraction of workflows, privacy rules preclude external models, and existing open-source VLMs that clear quality thresholds cost more to serve than human annotation. We present a deployed document-understanding system built on a Mixture-of-Experts VLM (35B total, 3B active), fine-tuned on in-house production data mixed with open-domain documents curated by a Difficulty-Aware pipeline for layout diversity, fact-extractability, and cross-model consistency. Fitting on a single H100 and serving heterogeneous workflows via prompting, the model leads all deployable (non-reasoning) baselines up to an order of magnitude larger. A quality-adjusted cost analysis, with confirmation and correction costs calibrated from production telemetry, shows it reduces expected costs by over 80% against the human baseline and by more than 50% against the best competing open-source model, while larger baselines remain economically unviable.

Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs

How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open problem. Existing work characterizes only broad trends (e.g., SFT dominates in low-data regimes), lacks a principled allocation framework, and does not examine whether the optimal ratio transfers across model sizes. We frame this problem in terms of near-optimality: rather than seeking a single optimal SFT-RL ratio, we characterize the near-optimal region, the set of allocations within a specified tolerance of peak performance. Empirically, this region is wide even for small tolerances (2-10%), widens with model scale, and transfers reliably from small proxy models to large target models. This yields a practical strategy: small proxy-model experiments suffice to identify a transferable near-optimal region, eliminating the need for exhaustive large-scale search. Our results hold consistently across tasks, model families, and both preference-based off-policy and reward-supervision on-policy RL methods. We further analyze how the asymmetry in annotation costs between SFT and RL data shifts the near-optimal region.

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 200 internal applications onto a single model by closing quality gaps identified through production error analysis along three axes: instruction following, function-calling, and internal task distribution. Quality is tracked by offline benchmarks stratified to production traffic and scored by deterministic verifiers or calibrated LLM judges. Rather than optimising all objectives jointly, which introduces cross-domain reward interference, we train a separate GRPO expert per axis and merge them via two-stage SLERP. Each expert's reward exposes a distinct failure mode, namely semantic collapse, over-calling, and verbosity hacking, each requiring a domain-specific fix. In non-reasoning mode the recipe surpasses a ${\sim}7\times$ larger by total parameters baseline on the in-house Arena with 69.6 to 65.8, instruction following with 0.85 to 0.83, and function-calling with 0.79 to 0.77, while lifting general dialogue benchmarks. The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.

Stopping the Unstoppable: When an unstoppable force meets a dashpot snubber

Atlas: A World Model for Spatial Intelligence

Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers

Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat systematic errors. We study how to learn a cheap autonomous policy from an online, expensive, and imperfect but informative VLM teacher. We propose SAGE (Selective Agent Guidance via Entropy), a framework that queries a VLM only when the learner is uncertain, executes the suggested action during training, and distills guidance into a lightweight Reinforcement Learning (RL) policy. Because VLM advice is not always reliable, SAGE can weight teacher-action distillation using environment-derived advantages rather than treating all suggestions as equally useful. Across sparse-reward visual reasoning and navigation tasks, SAGE learns policies that act without VLM guidance at evaluation time and improves over unguided RL in several environments, including settings where the learned policy exceeds its VLM teacher. The results show that selective guidance is most beneficial when the VLM can help the agent discover high-reward trajectories, and less useful when unguided exploration already succeeds or teacher actions do not lead to informative experience. SAGE also reduces VLM usage by prompting the teacher only on a fraction of training steps and requiring no VLM calls at deployment. Overall, our results suggest that VLMs don't need to be used as fixed policies to be useful; they can instead act as temporary, imperfect sources of guidance whose value is tested and internalized through interaction.

From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification

Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large label spaces, a common approach retrieves top-$K$ candidate labels by embedding similarity and prompt the LLM to choose among them. However, top-$K$ retrieval reduces the number of candidates but does not help the model tell similar ones apart. When two similar labels both appear as candidates, the model lacks the signal to choose correctly between them. We propose a framework that (1) identifies which label pairs the model struggles to distinguish, (2) expands the candidate set to include confusable labels, and (3) generates targeted rules to differentiate between similar candidates. The framework requires no fine-tuning, and the generated rules transfer to smaller, cheaper models. On three benchmarks (WOS, Flipkart, LEDGAR), our approach improves Macro F1 by up to 10.0pp over retrieval baselines, with smaller models (2B--20B) gaining up to 11.5pp via cross-model transfer.

A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains

Semiconductor supply chains face escalating risks from geopolitical tensions, geographic concentration, and rapid technological shifts, yet no scalable system continuously extracts, structures, and prioritizes risk intelligence from public corporate disclosures. We present an end-to-end pipeline that retrieves corporate documents for semiconductor companies and uses large language models (LLMs) to extract the risks and opportunities they describe. It organizes these into a knowledge graph linking each item to its category, sources, and related events, then merges duplicates and ranks them with a three-layer mechanism combining an algorithmic formula, an LLM relevance adjustment, and expert validation. Applied to five companies across the value chain, the pipeline produces 76,207 scored items, of which an independent check finds 92.6% valid. The automated rankings match expert judgment at an average Spearman correlation of 0.55 for risks and 0.72 for opportunities, and the resulting matrices identify trade restrictions as the dominant cross-company risk.

Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks

Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructing directions from loss-specific gradients to reduce conflict before optimizer transformation. However, even when the constructed direction is conflict-free, this property may not be preserved after optimizer transformation. Let $a_t$ denote the direction constructed by gradient surgery, $u_t$ the optimizer proposal, and $\mathcal{C}_t$ the conflict-free cone induced by the loss-specific gradients. We show that modern optimizers can transform $a_t$ through mechanisms such as historical state, adaptive scaling, preconditioning, or decoupled weight decay, so $a_t \in \mathcal{C}_t$ does not generally imply $u_t \in \mathcal{C}_t$. We refer to this optimizer-induced discrepancy in conflict-freeness between $a_t$ and $u_t$ as Gradient-Update Mismatch (GUM). Accordingly, we propose Gradient-Update Alignment (GUA), which projects $u_t$ onto $\mathcal{C}_t$ to obtain the aligned update $p_t$ and applies $p_t$ to the parameters. When the optimizer maintains internal state, GUA further adjusts this state toward targets reconstructed from the applied update. We conduct extensive experiments and find that GUM is widespread across momentum, adaptive, and curvature-based optimizers, with conflict rates reaching up to 86.3%. Across all PINN settings, GUA achieves conflict-free applied updates and consistently improves various gradient surgery methods, reducing the relative $L_2$ error by up to 98.2% in individual settings. Data and code are available at https://github.com/JingXiao10/GUA.

Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories

We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domains under one protocol, competition mathematics (MathNet-Retrieve; 500 queries, 117,088-item corpus) and embodied-agent trajectories (ALFWorld-derived; 118 queries, 336 trajectories). In mathematics the failure is complete: strict Hit@1 at the heaviest disguise tier is 0.0% for both production embedders (bootstrap 95% CI [0.0, 0.0]) while the correct item sits in the top 10 nearly always, and in 95.2 to 99.8% of misses the winner is more lexically similar to the query than the correct answer. In trajectories, where surface variation is incidental, the same models land at or near hypergeometric chance when gold must involve a different object, and below chance for all three embedders once gold must differ in object and receptacle: retrieval anchors on literal tokens, not task structure. A lexical reranker control hurts in mathematics and helps in trajectories (closing 26 to 36% of the gap, CIs excluding zero); its sign reveals whether a benchmark's surface variation is adversarial or incidental. An LLM reranker recovers 5 to 63% of the gap in mathematics and 43 to 76% in trajectories; direction replicates across three judges (all 21 cells positive), but effect sizes, tier profiles, and the outlier judge change with domain (paired differences excluding zero everywhere). Mathematics gains concentrate on well-known competitions (+19.8 points, CI [+6.7, +33.2], one of six cells), so part of the recovery is memorization. In a paired downstream experiment (210 queries, graders at 96 to 99% agreement), oracle retrieval was indistinguishable from adversarially bad retrieval (McNemar p = 0.678); the solver's 69.5% zero-shot accuracy is largely a truncation proxy (97 to 100% on finished answers), leaving no headroom.

BS: Take the Hint - Interactive Multitracer PET/CT Lesion Segmentation with a Scribble-Conditioned ResEnc U-Net

Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appearance of lesions across tracers. The autoPET/CT V challenge addresses this by making segmentation interactive: user scribbles marking foreground and background are supplied alongside the image, and the algorithm is expected to exploit them. We present our submission, a scribble-conditioned residual encoder U-Net operating on four input channels: CT, PET, and a sparse scribble map for each of foreground and background. The network is initialised from the autoPET-III winning weights and extended from two to four input channels, with the two scribble channels zero-initialised so that the pretrained representation is preserved exactly at initialisation. Every model is fine-tuned per fold from the corresponding autoPET-III fold checkpoint, so that no validation case is seen during pretraining. PET intensities are normalised against a per-scan aorta blood-pool reference derived from a CT segmentation, which removes tracer- and centre-specific scaling without requiring lesion labels. At inference the five fold models are ensembled by averaging their softmax outputs per sliding-window patch, before Gaussian-weighted stitching. On the challenge's five-fold split, with each fold evaluated on its own validation cases, mean Dice is 0.554 and mean lesion-level F1 is 0.528 without scribbles, rising to 0.751 and 0.733 after five correction rounds. About 85% of that gain follows the first scribble, and the spread between fold models narrows five-fold over the same rounds, so interaction largely compensates for how well or badly a given model segments unaided.

Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

Scientific equation discovery has long been central to scientific progress, proceeding through iterative cycles of hypothesis generation, observational testing, and refinement under scientific constraints. As LLM capabilities advance and their role in AI for Science expands, it remains an open problem whether they can genuinely discover scientific laws and how this ability should be evaluated. Existing evaluations, however, often either simplify discovery through synthetic settings or reuse published targets that may already be familiar to LLMs. We therefore introduce SCILAWS-BENCH, a benchmark for scientific law discovery built from published research and real scientific data. It comprises 118 problems drawn from 381 scientific papers, covering 291 candidate laws and roughly 8M real data points across six scientific disciplines. Each problem is instantiated in two complementary settings: (1) SCILAWS-REAL asks models to propose laws from fixed real observations and evaluates held-out predictive fit and scientific validity derived from the source literature, and (2) SCILAWS-PARALLEL asks models to actively query residual-calibrated worlds and recover synthesized hidden laws derived from published forms. This two-setting task design preserves each problem's scientific context while separately evaluating fixed-record law discovery and active recovery of a newly synthesized hidden law. We find that predictive fit can diverge from scientific validity, memorization shapes whether models reproduce or move beyond published formulas, and our best-of-N study reveals a selection bottleneck. Our work provides a paper-grounded benchmark and new empirical perspectives for evaluating AI for scientific discovery. Project page: https://yiyihum.github.io/SciLaws-Bench

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient algorithms and inherits their convergence guarantees towards Nash equilibria under an idealized model. Empirical evaluations across four benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of algorithms to posterior collapse in stochastic environments. We leave it as an open challenge.

SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue

Large Language Models (LLMs) are increasingly used in advice seeking and decision making that may affect social judgements. Despite stigma's profound effects on people and communities, benchmarks remain scarce. Existing general-domain evaluations typically rely on static prompts and fixed-format tasks, overlooking conversational contexts and audience effects in everyday communication. To address these gaps, we introduce SDARE-Bench, the first scenario-based benchmark evaluating both stigma detection and open-ended response generation in LLMs, comprising 1,138 dyadic queries and 1,388 group dialogue. Empirical results across 8 LLMs consistently demonstrate poor identification of stigma components, especially in group dialogues. In open-ended response generation, stigma expression was substantially higher in group settings than in dyadic, with weaker resistance to stigma and more unrealistic advice. Responses were evaluated using a classifier trained on 1,392 human annotated responses. In constructed group pressure settings, stigma expression rates further increased to a striking average of 97.5%. Our findings identify stigma response as a recurring LLM safety vulnerability, especially in socially complex conversational contexts.

US lawmakers demand investigation into admin's secret surveillance of Americans

Fine, I'll build my own text editor

Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis

Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires. Data-driven Q-matrix estimation remains challenging when assessments involve many correlated skills and when real response patterns depart from idealized generative assumptions. We introduce a novel quantum sparse autoencoder (QSAE) for Q-matrix estimation, which, to the best of our knowledge, is the first application of quantum machine learning (QML) to cognitive diagnosis. Overall, the QSAE embeds each student's binary response vector into a quantum circuit using an encoder, compresses it into a sparse latent representation, and maps that representation to the Q-matrix. We benchmark the QSAE against a classical autoencoder (CAE) across 60 simulated datasets and 9 real-world assessment datasets. The results reveal complementary strengths. Although the CAE partially achieves higher average accuracy under several simulation conditions, the QSAE is substantially more stable across replications, exhibiting lower variance in 49 of the 60 conditions. Moreover, on real assessment data, the QSAE outperforms the CAE on 6 of the 9 datasets. These findings suggest that the principal advancement of QML in this setting is not universal accuracy improvement, but enhanced robustness and capability to explore latent-structure complexity in real datasets.

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode

This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predictors, encoder trials evaluating their coding performance, and the LLM re-generating refined implementations based on the evaluation feedback. We first examine directly replacing the default Planar mode in the Fraunhofer Versatile Video Encoder (VVenC) under its faster preset. Experimental results demonstrate that the LLM-generated mode can outperform the conventional Planar mode on this lightweight toolset, achieving 0.18% bitrate savings with 0.4% complexity overhead on the standard benchmark. We further extend our evaluation to the Enhanced Compression Model (ECM). Leveraging newly introduced directional Planar modes, we investigate two integration strategies: directly replacing them, and introducing the LLM-generated predictor as an additional prediction mode with new syntax elements. The empirical results suggest that both strategies can yield coding gains under a constrained low-resolution setting. Overall, this study offers preliminary evidence and practical insights, highlighting both the potential and open challenges of LLM-based coding tool design.

Quoting Tarn Adams

They took the letters from me! I have to talk about dwarf behavior now. I can't even talk about dwarf AI. It doesn't exist. It's dwarf behavior , and they misbehave sometimes — Tarn Adams , co-creator of Dwarf Fortress Tags: ai , game-design

Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall

Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through controlled experiments, we find that forward Kullback-Leibler (KL) distillation--the standard KD formulation--with post-trained teachers behaves fundamentally differently during mid-training, an intermediate phase of self-supervised learning on curated corpora. Surprisingly, while forward KD simultaneously improves reasoning and factual recall during pre-training relative to standard next-token prediction (NTP), it instead slows factual recall acquisition during mid-training despite continued reasoning gains. We trace this stage dependence to an asymmetry in teacher confidence across data domains and the student's evolving knowledge state: teachers are more confident on procedural than knowledge-intensive data, while students acquire low-entropy factual knowledge earlier in training. To mitigate this imbalance, we propose Switch Distillation, a simple mid-training objective that distills on tokens where the teacher is confident, using teacher predictive entropy as a lightweight routing signal, and otherwise falls back to cross-entropy. Switch Distillation consistently outperforms existing distillation objectives across teacher sizes. Relative to standard NTP, it achieves 1.61-1.71x the reasoning performance and 1.13-1.19x the knowledge and commonsense performance while preserving 96.7-96.8% of factual recall. Crucially, these benefits persist after post-training: Switch Distillation closes the factual recall gap while maintaining 1.25-1.32x and 1.13-1.20x gains in reasoning and knowledge and commonsense, respectively.

Quill (YC W20) Is Hiring a Fullstack SWE

Sierpiński--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation

This paper introduces the Sierpiński-Knopp (SK) Wasserstein distance, a fast metric between persistence diagrams. The SK-Wasserstein distance, denoted $d_{\mathrm{SK}}$, maps diagram points and their diagonal projections to the unit interval via the Sierpiński-Knopp space-filling curve on the upper diagonal triangle. The encoded point sets are then efficiently matched via one-dimensional optimal assignment, in \(O(N\log N)\) steps, yielding an explicit diagonal-aware point assignment between the two input persistence diagrams. We show that the SK-Wasserstein distance controls the classical \(2\)-Wasserstein distance between diagrams, admits an explicit isometric embedding into a Hilbert space, and induces a positive-definite Gaussian kernel, making the resulting geometry directly compatible with Euclidean and kernel-based learning methods. A tighter surrogate dissimilarity, noted \(W_Γ\), is also introduced based on the point assignments along the curve. Experiments on 12 scientific collections comprising 227 diagrams show median per-collection speedup of \(d_{\mathrm{SK}}\) over state-of-the-art approximations of \(W_2\) is \(626\times\), while the aggregate speedup over the full benchmark is \(2100\times\). Average-linkage partitions obtained from \(d_{\mathrm{SK}}\) and \(W_Γ\) each exactly match the corresponding \(W_2\) partition on 8 of the 12 collections. Hilbert \(k\)-means and Gaussian spectral clustering, both based on \(d_{\mathrm{SK}}\), achieve mean adjusted Rand indices (ARI) of \(0.756\) and \(0.800\), respectively, with respect to the benchmark reference partitions, compared to \(0.750\) obtained by average linkage on \(W_2\). The Gaussian \(d_{\mathrm{SK}}\) kernel supports other kernel-based analysis tasks, as illustrated by its use for contiguous segmentation of ordered diagram collections in our experiments.

EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation

Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in free-form text, leaving their beliefs implicit and difficult to test or revise. We introduce EvoSCM, which equips scientific agents with explicit structural causal models that evolve as new experimental evidence is collected. EvoSCM maintains a population of competing SCM hypotheses, each encoding a candidate causal explanation of the environment, and evolves them through a closed discovery loop. In each round, the agent abduces latent mechanisms from accumulated evidence, designs discriminative interventions, and commits to falsifiable predictions that it tests through experimentation. Discrepancies between prediction and observation are inductively distilled into correction rules that revise the causal structures and mechanisms of each hypothesis, and the agent then deductively validates the revised population against accumulated evidence and structural consistency to guide the next round. We evaluate EvoSCM on DiscoverPhysics, a benchmark requiring agents to uncover the hidden dynamics of noncanonical physical worlds through experimentation. EvoSCM consistently improves scientific discovery over baselines, yielding more accurate explanations and predictions while making more effective use of experimental interactions.

Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data

A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data. We argue the opposite for the workloads enterprises actually run. A columnar relational engine fronted by a graph query language matches or exceeds native graph engines on analytical graph queries, and - decisively - scales past the point where in-memory graph engines fail. We further argue that the node/edge property graph is not a more faithful model of connected data but a re-encoding of relationships that already exist explicitly in relational tables; reconstructing them at query time is pure overhead. We present ClickGraph and its Databricks-dialect sibling DeltaGraph, systems that translate Cypher directly onto the native relational schema - the tables, columns, and foreign keys as they already exist - and execute in place on ClickHouse, Databricks, or in-process on lakehouse files, with no import and no separate cluster. Because the output is ordinary SQL, an underperforming query is an open optimization surface: it can be rewritten, and the engine itself extended. We support the argument with a peer system's own published benchmark, in which a columnar engine outruns Neo4j by two-to-four orders of magnitude, and with reproducible measurements across the LDBC Social Network Benchmark suite.

jasperai/t2i-technical-interactive-report

When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation

Interactive simulations increasingly evaluate policies in markets populated by language-model agents. Their outputs can look economic---prices, profits, consumer surplus, and welfare---without instantiating the behavior named in the claim. We audit this risk in a multi-turn buyer--seller testbed for configurable hotel transactions. An initial implementation reported welfare gains from two marketplace guardrails of +87.4, +35.0, and +28.8 across a Qwen2.5 1.5B--14B ladder. It also gave guarded and unguarded agents different offer schemas and choice procedures. Holding the schema and buyer chooser fixed changes the paired contrasts to +7.2, -13.9, and +23.8. The four largest 14B single-generation effects averaged +229; after three generations per profile-condition, they averaged +37.6 (95% bootstrap interval [-34.2, 109.3]), while generation residuals account for 49.9% of variation in this post-hoc probe. A seller-incentive check is non-monotone: increasing profit pressure produces less profit than the default seller prompt. Scripted positive controls show why this matters. A profit-maximizing seller already attains first-best welfare, so guardrails mostly redistribute and reduce welfare; they create welfare only when the seller is explicitly programmed to force inefficient bundles. We contribute a construct-validity contract separating incentive validity, protocol isolation, stochastic stability, and welfare accounting, and returning INVALID or INCONCLUSIVE before substantive policy claims. In our case, the original estimate is INVALID under protocol isolation, while the controlled study remains INCONCLUSIVE under incentive validity and stochastic stability. The case does not show that guardrails are ineffective; it shows their apparent value is unidentified until the simulated agents and protocol pass these checks.

TempCloze: Can Video-LLMs Identify the Missing Middle?

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly long-take and egocentric videos. We construct same-source distractors along three dimensions: Semantic asks what event should happen, Alignment probes when it should occur, and Progression tests how it should unfold, while shared scenes and objects reduce appearance cues. Our evaluation of 10 proprietary and 21 open-source Video-LLMs reveals Alignment as the primary bottleneck: models often recognize plausible semantic content and local event progression but struggle with temporal alignment. We further conduct error pattern and behavioral sensitivity analyses on TempCloze-Mixed and TempCloze-Hard with four representative models to examine where errors arise and how candidate order, context direction, visible span, frame density, and test-time scaling influence model choices.

Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s

Whistleblower warns Postal Service mail ballot system has catastrophic problems

LatentPress: Context Compression Beyond Text and Vision

Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference. A small reader-matched writer compresses $4$-$16\times$ while training only an adapter (4.2M-26.2M parameters, $\sim\!0.1\%$ of the decoder). On LongMemEval, LatentPress reaches $0.504$ accuracy at $7.70\times$ compression versus $0.490$ for uncompressed evidence, outperforming text summaries (0.184) and OCR-based compression (0.426 to 0.312). On LongBench-QA, in-domain writers match or exceed raw-context reading at $4$-$8\times$ compression, while $16\times$ trails raw. Writing takes 43ms per conversation, roughly an order of magnitude faster than text summarization or OCR reconstruction, and reading is $5$-$9\times$ faster than raw context or cached OCR. We validate the interface under two transfer settings, zero-shot from UltraChat to LongMemEval memory QA and from LongMemEval-derived QA to unseen LongBench document domains, establishing direct soft tokens as a practical machine-facing context interface beyond text and vision. The implementation of the experiments could be found at: https://github.com/xuyd16ai/context_softtoken_compress .

Movie Scene Map – 13,312 films, series, games, anime and manga

Thanks to Lake Ontario, MapQuest is popular all over again

Rethinking Learnability in Offline Data-driven Optimization

Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization improves the efficiency of BBO algorithms by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial attention because it requires no additional online evaluations. Many offline optimization methods have been proposed, but a fundamental question remains unanswered: what learnability is sufficient for offline optimization? Prior theoretical studies show that Probably Approximately Correct (PAC) learnability is insufficient, as the optimal region may remain poorly learned even when most regions are well learned. In this paper, we propose algorithm-dependent learnability, which requires accuracy only on the optimizer's trajectory. We prove that its value-query form is sufficient for representative discrete settings, including greedy and local search for submodular maximization, while its first-order analogue is sufficient for projected gradient descent on convex minimization. Motivated by this notion, we formalize a trajectory-learning framework comprising trajectory construction, trajectory modeling, and candidate generation, and analyze existing trajectory-based methods under it. We further propose Uncertainty-aware Gradient-guided Trajectory Learning (UGTL), which constructs locally coherent improvement trajectories reflecting plausible search paths, models them with conditional diffusion, and selects a diverse candidate set. On five Design-Bench tasks, UGTL achieves the best aggregate mean rank, $3.1/25$, among 25 methods. Controlled trajectory analyses and cross-architecture replacements confirm that our trajectory construction plays a significant role in the improvement.

GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, which requires agents with partial information to communicate under pressure. We find that language evolution does occur between LLM agents, that the resulting languages are compositional and morphologically productive, and that they deviate from the LLMs' English prior in ways that render them incomprehensible to humans. Moreover, we identify several qualities essential to this evolution: pressure towards efficiency; the strength of the models backing the agents; and access to a "postmortem" stage in which agents can agree on linguistic conventions. Importantly, we observe that different conditions govern the transmission of language to new agents. Specifically, we find that agents learn new languages from usage alone, take an active role in this learning, and that while stronger models are required for novel language emergence, weaker models can learn an existing language once it has emerged. Taken together, our results indicate that current LLMs have the potential for cumulative cultural evolution -- previously attested only in humans -- with mixed populations of agents developing capacities that go beyond their lowest common denominator.

Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. Across Claude Code and OpenClaw, the evolved guard substantially reduces attack success while maintaining a favorable safety-utility trade-off. On repeated GLM-5 runs, SkillSonar reduces ID ASR from 0.482 to 0.104 and OOD ASR from 0.606 to 0.115. Further analyses demonstrate transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers. Ablations further show that explicit safety responsibility assignment and the skill-native representation are both important to the observed gains.

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

PRs NOT Welcome: How Top AI Open Source Projects Are Managing Thousands of Contributors

Vercel’s AI SDK, Astro, Flue and tldraw are replacing drive-by community PRs with software factories, where teams of agents apply fixes and features.

Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an append-only event ledger folded incrementally into typed run state and compiled into per-consumer views, and evaluate it for both consumers against deterministic ground truth. For the observer side, evaluated with an LLM reader as proxy, the compiled view answers monitoring questions using approximately 14x and 15x fewer input tokens (by reader) and at 5-7x lower cost than a budget-capped single-call reading of the raw trace, with higher accuracy (0.85-0.87 versus 0.48). Because the questions were co-designed with the view schema, we treat the token and cost reduction, conditional on schema coverage, as the transferable result. For the agent, on 120-link sequential-dependency tasks, mechanisms that maintain the task's running statistic in per-step state succeed where full-context prompting fails (30/30 versus 8/30 under a clean protocol, n=30, labeled descriptive owing to benchmark-system co-development); a prompt-level scratchpad matches the fold's accuracy at lower cost, and a two-arm decomposition attributes the fold's accuracy to its deterministic aggregate and its cost advantage to its compactness. The fold's remaining value over cheaper alternatives is deterministic auditability and serving the observer from the same state. We derive eleven candidate requirements for trace folding from observed failures and delimit them with an order-sensitive task family on which the fold ceases to help. Code, benchmarks, a regenerable synthetic corpus, and all workbench traces are released.

AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval

Composed image retrieval (CIR) retrieves a target image from a reference image and a text modification. This paper studies metadata-available CIR reranking, where a fixed CIR model first returns a candidate pool and gallery metadata is then used for second-stage concept-guided scoring. We introduce AutoConcept, a training-free reranker that converts concept evidence into an interpretable memory. AutoConcept filters noisy concepts, activates query-relevant positive constraints with an auxiliary negative penalty, and combines base retrieval scores with metadata-based concept-candidate alignment through inference-time calibration. On FashionIQ, AutoConcept yields significant early-rank improvements over WeiMoCIR and consistent plug-in gains on LinCIR candidate pools. Metadata-aware controls show that structured concept memory adds signal beyond direct query-text and extracted-attribute matching, while a query-only variant further supports the effectiveness of concept-level reranking. A supplementary real-human concept-label study indicates that the same memory interface can consume participant-provided evidence. These results position AutoConcept as an interpretable concept-memory reranker for product-style CIR galleries with available metadata.

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior work often attributes this failure to gradient conflict, we propose a fundamentally different Fisher-geometric explanation: safety Fisher is low-rank, and alignment makes the safety geometry flatter while preserving an output-routing pathway. After 100 benign fine-tuning examples, this pathway is selectively re-sharpened in output-side MLP modules, explaining the asymmetric fragility: safety can collapse to high attack success rates, while general utility degrades mildly. The routing view also explains why few safety examples can restore refusal behavior, indicating that internal safety-relevant representations are preserved. Finally, we show that LoRA and ASAM mitigate early collapse by suppressing output-side sharpness, but their protection weakens at larger fine-tuning scales. Overall, safety failure is best understood as a disruption of a low-rank output-routing mechanism

Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds

Dexterous manipulation policies learned by imitation are typically evaluated for robustness to variation in scenes, objects, or instructions, but their performance across task execution speeds is less often examined. This leaves open how much temporal robustness a learner retains relative to the expert it imitates. We compare an expert and learner under the same task conditions, initial-condition draws, and speedup factors. We instantiate the evaluation in ParcelStow, a contact-rich task in which the robot acquires, reorients, and inserts a parcel. The demonstrations span the speedup range for the manipulation phases after parcel acquisition. A scripted expert and an Action Chunking with Transformers (ACT) policy trained from the expert's demonstrations both achieve 100 percent task success at nominal speed. Their success rates diverge within the demonstrated range: at its maximum, expert success is 84 percent and ACT success is 53 percent. Two ACT policies with different parameter initializations show similar degradation, decreasing by 34 and 48 percentage points from nominal speed to the maximum demonstrated speed, compared with 16 points for the expert. Stage-level analysis shows that 35 of ACT's 47 failures at the maximum demonstrated speed are insertion misalignments. Under the relative-motion handoff, every ACT acquisition retains the parcel through reorientation and transfer in free space, but only 64 percent complete the overall task, compared with 95 percent after expert acquisition. Across all evaluated policies and speeds, none of the 414 acquisitions without force closure completes the task. Equal nominal task success therefore does not imply preservation of expert performance across execution speeds. Code, data, and evaluation scripts are available at https://github.com/coenwerem/parcelstow.

Play Store blocks AuroraStore, hurting GrapheneOS users

Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning

Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state to a diffusion denoiser and remove its timestep conditioning, leaving a single shared update that can be run to arbitrary depth. The result is an anytime solver: accuracy keeps improving with inference depth far beyond the rollout lengths and backpropagation window used in training, reaching 99.90% exact solve on Sudoku-Extreme. We also obtain 98.93% solve rate on Maze-Unique. Surprisingly, progressive denoising is unnecessary at inference: holding corruption at its maximum by replacing every non-clue variable with fresh Gaussian noise at each step retains near-perfect solving and converges to stable solutions. This simple noise-injection mechanism enables a single trajectory to efficiently explore the solution space and settle on the correct answer without parallel rollouts, candidate selection, or external verifiers required by prior reasoning models. Nonetheless, ordered annealed corruption remains critical during training, which suggests that diffusion's primary contribution to our anytime solver is not a sampling procedure at inference, but a denoising training curriculum.

Dwarf Fortress' creator says the industry's in shambles over AI

Edge-Girth as a Structural Edge Feature for Graph Neural Networks

Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot tell apart receive identical representations, however deep or wide the network. A common remedy augments node or edge features with precomputed structural descriptors, most often counts of a fixed small subgraph such as triangles or longer cycles, but such counts require committing in advance to the size of the substructure counted, a choice usually made blind to the data. We study a descriptor that avoids this choice. The edge-girth of an edge is the length of a shortest cycle through it, and its multiplicity is the number of such shortest cycles; together they form a per-edge invariant that reports cycles of arbitrary length, computable exactly by a single breadth-first search per edge. Injected into a gated message-passing architecture, EGAGNN, it reaches a test MAE a factor three below the closest gated comparator on the ZINC-12k regression benchmark at 104k parameters; against bounded cycle-counting descriptors under the same architecture, it matches only a dictionary counting cycles up to length eight, using twice as many channels, while a dictionary capped at length four performs no better than no structural information at all. On graph discrimination we prove a matching limitation: on graphs where every edge sees the same number of shortest cycles of the same length, the descriptor becomes constant and any model built on it collapses back to the 1-WL bound. This holds without exception across all 400 pairs of the BREC benchmark: not one of the 90 such pairs is distinguished.

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Changing this harness while holding model weights fixed can substantially alter task performance. Current agent evaluations typically report downstream performance under a chosen harness, leaving a model's ability to develop the harness itself comparatively underexplored. We introduce HarnessDev, a benchmark that shifts the unit of evaluation from task outputs to runnable infrastructure. HarnessDev covers two stages. In Creation, the agent starts from a minimal seed and a small number of cases, then builds a complete execution system. In Evolution, it starts from its own created harness and iteratively revises it using downstream execution feedback, with the goal of improving benchmark performance. We then evaluate each constructed harness on capability (task success on held-out benchmarks) and efficiency (execution-token cost). The reported Creation results cover six creator LLMs, four domains, and five downstream benchmarks totaling 2,207 unique downstream instances, with hidden evaluation tasks withheld from development. We find that generated harnesses remain substantially behind mature human-engineered references on code and on search and research, while matching or exceeding the selected references on writing and machine-learning experimentation, with large variation in execution cost. Evolution produces some performance gains, but they are unstable and transfer only partially to held-out tasks. Experiments with a fixed runtime model further show that the gains depend strongly on the model executing the harness, indicating limited transfer across models.

Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation

Scientific citations carry rhetorical intent. Scholars may cite prior work positively (supporting), negatively (contrasting), or neutrally (mentioning). As large language models (LLMs) increasingly assist scientific writing, whether they reproduce citations with the same rhetorical intent as humans remains unclear. We introduce a masked-citation task to compare human and LLM-generated citation behavior. For each citation context, an LLM generates a replacement citation sentence, producing a counterfactual corpus directly comparable to human citation. We analyze what, whom, and how models cite, using an LLM-as-a-judge to classify citation intent and a 20-million-edge coauthorship network to measure social distance between cited authors. Across six popular LLMs and 1,746 top NLP conference papers (63k+ contexts, 132k+ citations), three patterns emerge: (1) Compared with human citation, LLMs cite significantly less critically; (2) LLMs over-cite popular and older papers, a tendency amplified for contrasting citations where human writing more often draws on recent, niche work; (3) Whereas humans often cite within their close social network, especially for supporting citations, LLMs tend to draw on more socially distant authors. Together, these differences are double-edged: LLM citation reaches beyond a scholar's close collaborators while being less critical and amplifying visibility bias, reshaping the rhetoric and reach of scientific citation.