AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsTheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving
arXiv:2610.16733v1 Announce Type: cross Abstract: We present a suite of 50 unpublished research-level theoretical physics problems with verifiable answers. Without AI assistance, a typical problem in our collection could…
- arXiv cs.AIresearchLotus: Learning to Understand Time-series by Learning to Forecast
arXiv:2610.18877v1 Announce Type: cross Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervision encourages linguis…
- arXiv cs.AIresearchInverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data
arXiv:2610.18878v1 Announce Type: cross Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requires reasoning trac…
- arXiv cs.AIresearchDo Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders
arXiv:2610.18879v2 Announce Type: replace-cross Abstract: Protein function annotation operates over an expanding label space, making class-incremental learning (CIL) a natural framework for incorporating newly discovered…
- arXiv cs.AIagentsDo Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening
arXiv:2610.18880v1 Announce Type: cross Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A difficult case arise…
- arXiv cs.AIagentsFollowing the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection
arXiv:2610.18881v1 Announce Type: cross Abstract: Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a con…
- arXiv cs.AIresearchToken Utility for On-Policy Distillation via Local Trust-Region Optimization
arXiv:2610.18883v1 Announce Type: cross Abstract: Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-student disagreement,…
- arXiv cs.AIresearchPersonalising Deformable Image Registration with Clinical Context and Deformation History for Adaptive Radiotherapy
arXiv:2610.18926v1 Announce Type: cross Abstract: Adaptive radiotherapy must account for anatomical changes during treatment, but doing so depends on reliably mapping targets, organs at risk and dose across serial images…
- arXiv cs.AIresearchNon-Abelian quantum Hall states at strong Landau level mixing: finding anyons with first-principles AI
arXiv:2610.18967v1 Announce Type: cross Abstract: Non-Abelian anyons, strange particles forming the basis of fault-tolerant topological quantum computing, are predicted to emerge in fractional quantum Hall states at even…
- arXiv cs.AIresearchEvaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali
arXiv:2610.19003v1 Announce Type: cross Abstract: Abstractive summarization remains challenging across languages, where linguistic quality and factual consistency may diverge, particularly in low-resource settings. We pr…
- arXiv cs.AIagentsCyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
arXiv:2610.19005v2 Announce Type: replace-cross Abstract: AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in…
- arXiv cs.AIresearchScaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction
arXiv:2610.19015v1 Announce Type: cross Abstract: Real measurements are too limited to train an accurate indoor pathloss predictor that works across a wide range of buildings. Large-scale synthetic pretraining offers a w…
- arXiv cs.AIresearchWho Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment
arXiv:2610.19035v1 Announce Type: cross Abstract: Pluralistic alignment needs to accommodate diverse preferences under limited human feedback. Using AI simulators to label preference comparisons reduces annotation costs,…
- arXiv cs.AIresearchLoss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models
arXiv:2610.19042v1 Announce Type: cross Abstract: Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we examine this quest…
- arXiv cs.AIresearchGraph Coarsening Enables Escaping Local Optima in Compute-Constrained Nonconvex MAX-CUT
arXiv:2610.19043v1 Announce Type: cross Abstract: Because its binary optimization landscape contains exponentially many local optima, MAX-CUT is highly sensitive to initialization. We study Particle Polynomial Relaxation…
- arXiv cs.AIresearchHow Inner Optimizers Shape Replica Scaling
arXiv:2610.19064v1 Announce Type: cross Abstract: Training large language models (LLMs) across geographically distributed and poorly interconnected compute pools or data centers has become a topic of significant interest…
- arXiv cs.AIresearchRevisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap
arXiv:2610.19065v1 Announce Type: cross Abstract: Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. Howeve…
- arXiv cs.AIresearchBeyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization
arXiv:2610.19084v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) uses feedback from model responses to improve prompts automatically. However, its effectiveness is usually measured through overall sc…
- arXiv cs.AIresearchDexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation
arXiv:2610.19089v2 Announce Type: replace-cross Abstract: Achieving human-like dexterous manipulation remains a central challenge in robotics. Learning from human hand-object interaction (HOI) datasets offers a promising…
- arXiv cs.AIagentsTowards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reas…
- arXiv cs.AIresearchFrom Copying to Composition: How Language Models Develop In-Context Learning
arXiv:2610.19113v1 Announce Type: cross Abstract: In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextu…
- arXiv cs.AIresearchGenesis Steering: Better Activation Steering Through Training Data
arXiv:2610.19114v2 Announce Type: replace-cross Abstract: Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering…
- arXiv cs.AIresearchUnlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming
arXiv:2610.19121v1 Announce Type: cross Abstract: Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models. However, existing methods can cause reasoning performance to…
- arXiv cs.AIagentsLearning in Orbit: Onboard Training and Closed-Loop Attitude Control with a Thermal Segmentation Model on a Spacecraft
arXiv:2610.19122v1 Announce Type: cross Abstract: Deep space missions increasingly require spacecraft capable of autonomously operating in environments with communication delays and bandwidth limitations. A key enabler o…
- arXiv cs.AIresearchPairIT: Autoregressive Transformers for Low-Data Molecule Optimization
arXiv:2610.19123v1 Announce Type: cross Abstract: Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, practical use cases…
- arXiv cs.AIresearchImagining Goals with Geometric Horizon Models for Policy Generalization
arXiv:2610.19129v1 Announce Type: cross Abstract: Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily applied zero-shot or e…
- arXiv cs.AIresearchCAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition
arXiv:2610.19134v1 Announce Type: cross Abstract: Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual a…
- arXiv cs.AIresearchMA-Bench: Measuring Operational Planning in Language Models
arXiv:2610.19138v1 Announce Type: cross Abstract: How well can a language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists? We introduce Mission A…
- arXiv cs.AIresearchDiagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection
arXiv:2610.19178v2 Announce Type: replace-cross Abstract: Before deploying clinical prediction models, their reliability must be assessed to ensure safe use. Errors may arise from distribution shifts between training and…
- arXiv cs.AIresearchFinite-sample certification of coverage regret for budgeted document selection under adaptive stratified auditing
arXiv:2610.19207v1 Announce Type: cross Abstract: Selecting a budget-constrained set of documentary fragments, for instance the knowledge base of a retrieval-augmented generation system, raises a statistical question: ho…
- arXiv cs.AIresearchTitan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules
arXiv:2610.19210v1 Announce Type: cross Abstract: Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference requires increasingl…
- arXiv cs.AIresearchGeneralizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
arXiv:2610.19211v1 Announce Type: cross Abstract: While causal discovery methods have matured for complete data, such algorithms for handling missing values remain limited. We establish general sufficient conditions unde…
- arXiv cs.AIagentsNarrowing the Collaboration Gap, Probably
arXiv:2610.19215v1 Announce Type: cross Abstract: Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents concisely communica…
- arXiv cs.AIresearchDo Syntax Heads Influence Model Behavior?
arXiv:2610.19231v1 Announce Type: cross Abstract: Transformer language models develop attention heads that specialize in syntactic relations, for example, attending from verbs to their subjects. Do these heads play a cau…
- arXiv cs.AIresearchRefined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction
arXiv:2610.19246v3 Announce Type: replace-cross Abstract: Equivariant structure-prediction pipelines alternate coordinate updates with the construction of a k-nearest-neighbour (kNN) graph whose membership is a discrete,…
- arXiv cs.AIresearchCopy-Paste Language Models
arXiv:2610.19247v1 Announce Type: cross Abstract: Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can be improved through…
- arXiv cs.AIresearchMIND: Instruction-Conditioned Incremental Grounding for Robots
arXiv:2610.19262v1 Announce Type: cross Abstract: Robots following persistent language instructions must decide which cached room judgments remain valid as their environment changes. We present MIND (Maintenance via INst…
- arXiv cs.AIagentsBeyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
arXiv:2610.19264v1 Announce Type: cross Abstract: Agent skills are Markdown documents that a tool-using agent reads as instructions and then acts on with the privileges of the session that loaded them. Installing one gra…
- arXiv cs.AIresearchWhose Data, Whose Benchmark? A User-Centric Framework for Auditing Evaluation Resources
arXiv:2610.19268v1 Announce Type: cross Abstract: Benchmarks shape how model capabilities are measured and interpreted, yet their scores can obscure whose conventions, contexts, and judgments define successful performanc…
- arXiv cs.AIresearchExploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series
arXiv:2610.19270v1 Announce Type: cross Abstract: The ecological insurance theory posits that diverse forests are more resilient and better able to adapt to changing environmental conditions. Increasing drought and heat…
- arXiv cs.AIresearchDimension-Free Scaling Laws for Size Generalization: An Exponential Separation
arXiv:2610.19279v1 Announce Type: cross Abstract: Modern machine learning models increasingly operate on variable-size structured data, such as sets and graphs. A central requirement is \emph{size generalization}: the ab…
- arXiv cs.AIresearchDTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision
arXiv:2610.19302v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and teacher diverge,…
- arXiv cs.AIresearchLLM-jp-4 Technical Report
arXiv:2610.19331v1 Announce Type: cross Abstract: This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, and practical usabi…
- arXiv cs.AIagentsWhy Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States
arXiv:2610.19342v2 Announce Type: replace-cross Abstract: Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's per…
- arXiv cs.AIresearchAsymptotic Behavior of Transformers
arXiv:2610.19358v1 Announce Type: cross Abstract: In this paper we study the behavior of transformer networks generating text over long periods of time. We show that even a three-token, single-layer attention-only transf…
- arXiv cs.AIresearchTail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
arXiv:2610.19362v1 Announce Type: cross Abstract: Best-of-N sampling is a simple inference-time scaling strategy for large language models, yet its behavior under incomplete reward models remains poorly understood. We st…
- arXiv cs.AIagentsBeyond Corrected Actions: Training LLM Agents on Textual Critiques
arXiv:2610.19367v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions.…
- arXiv cs.AIagentsPolicy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards
arXiv:2610.19372v1 Announce Type: cross Abstract: Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded afterward. We ask…
- arXiv cs.AIresearchEvaluating Compressed Memory: Dependence, Utility, and Content Benefit
arXiv:2610.19373v1 Announce Type: cross Abstract: Does a language model answer better because its compressed memory contains useful document information? Replacing memory vectors with zeros can lower a trained model's sc…
- arXiv cs.AIresearchELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies
arXiv:2610.19388v2 Announce Type: replace-cross Abstract: Massively multilingual speech modeling has made remarkable progress in recent years, yet existing training resources and benchmarks still underrepresent much of t…