AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsDrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
arXiv:2610.23791v1 Announce Type: new Abstract: Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable ag…
- arXiv cs.AIresearchFuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper
arXiv:2610.23796v1 Announce Type: new Abstract: Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is domina…
- arXiv cs.AIresearchBeyond SAEs: Consistent Concept Discovery with Sparse Coding
arXiv:2610.23801v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) explain foundation model representations by decomposing activations into sparse combinations of learned dictionary atoms. However, the learned di…
- arXiv cs.AIagentsSelf-Building Labs
arXiv:2610.23826v2 Announce Type: replace Abstract: Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experimen…
- arXiv cs.AIagentsAI-Driven Reproducibility and Analytical Robustness in Scientific Discovery
arXiv:2610.23845v1 Announce Type: new Abstract: Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We inv…
- arXiv cs.AIagentsCausalEvo: Causal Skill Self-Evolution for Health LLM Agents
arXiv:2610.21016v1 Announce Type: cross Abstract: Large language model (LLM) agents for health can accumulate reusable textual skills from task feedback, such as calculation criteria, measurement time points, and formula…
- arXiv cs.AIagentsWhen is a large language model a good calibration agent? Physics-labeled prompting for budgeted engineering simulator calibration
arXiv:2610.22379v1 Announce Type: cross Abstract: Calibrating expensive engineering simulators requires tuning model parameters to match reference data, a process heavily constrained by computational costs. This study in…
- arXiv cs.AIresearchEliciting Specifications: When Does Interactive Clarification Help?
arXiv:2610.22382v1 Announce Type: cross Abstract: LLMs can generate Lean specifications from task descriptions, but those descriptions are often underspecified or ambiguous and may omit verifier-relevant edge cases, yiel…
- arXiv cs.AIagentsTowards Adaptive and Real-Survey-Aligned Simulated Urban Mobility Behaviour of Generative Agents
arXiv:2610.22407v1 Announce Type: cross Abstract: In existing agent-based simulations of multimodal urban mobility, agents, representing humans, choose their travel modes either using discrete choice or machine learning…
- arXiv cs.AIresearchFrom Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory
arXiv:2610.22416v1 Announce Type: cross Abstract: Automatic melody harmonization is often evaluated through individual compositions or data-driven corpus models. This study examines whether an explainable harmonic decisi…
- arXiv cs.AIresearchReally Need Recursion? Revisiting One-pass Registration with Multi-level Multi-space Contextual Guidance
arXiv:2610.22423v1 Announce Type: cross Abstract: Deformable image registration is a fundamental challenge in medical image analysis. Recent deep learning-based methods typically adopt either one-pass architectures that…
- arXiv cs.AIresearchRecoverability-Controlled Safety Miscalibration in Large Language Models
arXiv:2610.22425v2 Announce Type: replace-cross Abstract: Safety-aligned language models are expected to refuse harmful requests while remaining useful for benign ones. However, because many evaluations score only the fi…
- arXiv cs.AIresearchTRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference
arXiv:2610.22435v1 Announce Type: cross Abstract: Distributed Transformer inference across co-located edge devices is fundamentally communication-bound, as exchanging activations between sequence-parallel partitions domi…
- arXiv cs.AIresearchSparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
arXiv:2610.22439v1 Announce Type: cross Abstract: Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned informat…
- arXiv cs.AIagentsDriveWorld3D Evidence Constrained 3D World Modeling and Generative Simulation for Real-World Autonomous Driving
arXiv:2610.22450v1 Announce Type: cross Abstract: Three dimensional modeling for autonomous driving must continuously estimate road geometry, obstacle occupancy, traffic participant behavior, and observational uncertaint…
- arXiv cs.AIresearchPolitical Narratives in the 2024 Moldovan Presidential Election: Stance, Amplification, and Influence
arXiv:2610.22464v1 Announce Type: cross Abstract: Social media platforms play a central role in shaping political discourse during elections, particularly in geopolitically contested regions. We study how political narra…
- arXiv cs.AIresearchProgressive Misalignment Can Emerge from Benign Recursive Self-Distillation
arXiv:2610.22467v1 Announce Type: cross Abstract: Training models on their own outputs has attracted widespread attention as a possible route to advance AI capabilities. One prominent approach is self-distillation, where…
- arXiv cs.AIresearchUpper bounds on the number of causal pieces in spiking neural networks
arXiv:2610.22484v1 Announce Type: cross Abstract: The input space of single-spike neural networks decomposes into causal pieces, and the number of causal pieces has been shown to provide a lower bound on the approximatio…
- arXiv cs.AIagentsAuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems
arXiv:2610.22511v1 Announce Type: cross Abstract: Evaluating language models and agents requires combining benchmark accuracy, judge-based assessment, runtime performance, tool-use behavior, and retrieval quality. Differ…
- arXiv cs.AIresearchMitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization
arXiv:2610.22586v1 Announce Type: cross Abstract: We study explanation fairness in hate speech detection. High classification performance does not always mean that a model produces equally plausible explanations for diff…
- arXiv cs.AIresearchCan LLMs predict the outcomes of machine learning experiments?
arXiv:2610.22599v1 Announce Type: cross Abstract: Recent advances in AI make Recursive Self-Improvement (RSI) increasingly plausible. Large Language Models (LLMs) can already propose, select, and run Machine Learning (ML…
- arXiv cs.AIresearchThree LiDARs, Twenty-Five Datasets: Cross-Source Generalization in Tree-Species Recognition
arXiv:2610.22606v1 Announce Type: cross Abstract: FOR-species20K is the largest public LiDAR benchmark for tree-species classification, pooling 25 independently collected terrestrial, mobile, and airborne laser-scanning…
- arXiv cs.AIresearchStratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning
arXiv:2610.22626v1 Announce Type: cross Abstract: Advanced persistent threats (APTs) are a major concern in federated learning (FL) deployments in critical sectors such as healthcare, and finance. Traditional defense mec…
- arXiv cs.AIresearchChoosing models for network-wide freeway speed estimation and forecasting from sparse fixed sensors
arXiv:2610.22630v2 Announce Type: replace-cross Abstract: Most freeway agencies have fixed detectors on only part of their network but need speeds for all of it. This paper compares methods for estimating current and nex…
- arXiv cs.AIresearchA Plausible Explanation Is Enough to Mislead Multimodal Judges
arXiv:2610.22631v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly serve as judges in training and evaluation pipelines, often assessing answers together with explanations. Although A…
- arXiv cs.AIresearchToMStories: Interpreting Theory-of-Mind in Synthetic Narratives
arXiv:2610.22632v1 Announce Type: cross Abstract: Understanding people often requires inferring what they feel or want from how they behave rather than from what they state outright. We ask whether language models can ma…
- arXiv cs.AIresearchMeasuring Mechanistic Uncertainty in Large Language Models via Causal Robustness
arXiv:2610.22636v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in critical domains, where their susceptibility to hallucinations makes reliable and interpretable uncertainty quantifi…
- arXiv cs.AIresearchHard Instances on Demand
arXiv:2610.22637v1 Announce Type: cross Abstract: The conclusions of an experimental study of algorithms are only as good as the instances they are run on. Benchmark libraries for well-studied problems took decades to cu…
- arXiv cs.AIresearchDiverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for Enhancing RL Exploration
arXiv:2610.22665v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for improving the reasoning capabilities of LLMs. However, the role of supervised…
- arXiv cs.AIagentsAlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
arXiv:2610.22684v1 Announce Type: cross Abstract: Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model…
- arXiv cs.AIagentsExplore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries
arXiv:2610.22688v1 Announce Type: cross Abstract: Large language model agents must discover relevant tools from large libraries, e.g., thousands of tools, as new needs arise during task execution. When several candidates…
- arXiv cs.AIagentsNoveltyScope: A Multi-Agent Research Assistant for Evidence-Grounded Novelty Assessment of Scientific Papers
arXiv:2610.22703v1 Announce Type: cross Abstract: NoveltyScope is a prototype that compares a scientific paper with retrieved prior work and produces a structured report and a five-level novelty score. The system extract…
- arXiv cs.AIresearchARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking
arXiv:2610.22717v1 Announce Type: cross Abstract: Large reasoning models solve complex problems through long chains of thought, in which prior work has documented failure modes such as overthinking, underthinking, and un…
- arXiv cs.AIresearchOrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting
arXiv:2610.22727v1 Announce Type: cross Abstract: We study the conditional distribution of limit-order volume submitted over the next five minutes, given the current order book and recent order flow. The task requires ca…
- arXiv cs.AIresearchNext Token or Vector? Learning How Far to Decode
arXiv:2610.22788v1 Announce Type: cross Abstract: Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together. We propose CADENCE (Context-Adaptive DEcoding)…
- arXiv cs.AIagentsSelf-Evolving Coding Agents via Harness-Policy Optimization
arXiv:2610.22791v1 Announce Type: cross Abstract: Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that med…
- arXiv cs.AIresearchPrune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning
arXiv:2610.22792v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) on proprietary records enables domain adaptation but introduces two challenges: (i) privacy leakage of memorized private data, su…
- arXiv cs.AIagentsSTRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases
arXiv:2610.22795v1 Announce Type: cross Abstract: In autonomous driving, perceiving surrounding objects is not enough: failing to understand how they move and interact over time can lead to dangerous decisions. Evaluatin…
- arXiv cs.AIresearchThe Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls
arXiv:2610.22841v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) faithfulness matters for monitoring, explaining and safely deploying large language models, yet it has been studied mostly in English. Languages di…
- arXiv cs.AIresearchSample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
arXiv:2610.22852v1 Announce Type: cross Abstract: Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can imp…
- arXiv cs.AIresearchUncertainty-Aware Budget Allocation for Efficient LLM Tree Search
arXiv:2610.22858v1 Announce Type: cross Abstract: Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal util…
- arXiv cs.AIagentsCooperation Without Adaptation: LLM Agents in a Collective-Risk Dilemma
arXiv:2610.22882v1 Announce Type: cross Abstract: Language-model agents are increasingly deployed to act on behalf of people in settings where individual decisions shape shared outcomes. We examine whether five productio…
- arXiv cs.AIresearchLearning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance
arXiv:2610.22885v1 Announce Type: cross Abstract: Classifier-free guidance (CFG) is a standard component of conditional diffusion models, and guided generation performance has become the \textit{de facto} measure of stat…
- arXiv cs.AIresearchBatched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?
arXiv:2610.22887v2 Announce Type: replace-cross Abstract: Long rollout windows make reinforcement learning with verifiable rewards (RLVR) expensive, yet simply shortening them can remove the correctness signal: when ever…
- arXiv cs.AIresearchCompetence-Based Evaluation of Logical Reasoning in Large Language Models
arXiv:2610.22894v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have brought impressive performance across diverse tasks; however, shortcomings remain in logical reasoning, including inc…
- arXiv cs.AIresearchHAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies
arXiv:2610.22895v1 Announce Type: cross Abstract: Physical reasoning about humans in videos has largely focused on everyday interactions, where contact, pressure, pose, and motion support embodied perception and contact-…
- arXiv cs.AIresearchCOMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language Learning
arXiv:2610.22907v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP retain zero-shot recognition ability, but their open-world use often requires task-agnostic continual learning: tasks arrive se…
- arXiv cs.AIresearchMany Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism
arXiv:2610.22937v1 Announce Type: cross Abstract: Language models often abandon a correct answer when the prompt contains a cue, a hint toward a wrong option such as "I think the answer is B." Sycophancy and related bias…
- arXiv cs.AIresearchAligning Language Models Towards Counterfactual Invariance
arXiv:2610.22942v1 Announce Type: cross Abstract: Small variations in prompt characteristics can meaningfully alter the semantics, tone, and contextual assumptions of large language model outputs. Such characteristics ca…
- arXiv cs.AIresearchNL2SQL with Iterative Self-Refinement
arXiv:2610.22968v1 Announce Type: cross Abstract: Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unrel…