AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhen the Same Prompt Gives Different Answers (and the Same Answer Isn't Always Right): A Taxonomy of Failure Mechanisms, Testing, and Mitigation Strategies for LLM-Assisted Evidence Synthesis Read-and-Evaluate Tasks
arXiv:2610.39070v1 Announce Type: new Abstract: LLM read-and-evaluate tasks include study screening, data extraction, risk-of-bias assessment, and critical appraisal in the evidence synthesis field. These task differ in…
- arXiv cs.AIresearchCertified Access: Test-Time Compute on Conservative Physics-Structured AI Memory
arXiv:2610.39073v1 Announce Type: new Abstract: Test-time compute mechanisms, such as retries, confidence-based escalation and non-local routing, are conventionally deployed as black-box additions to trained models. They…
- arXiv cs.AIresearchReasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models
arXiv:2610.39182v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly described as acquiring "reasoning" skills after reinforcement learning with verifiable rewards. However, whether these gains r…
- arXiv cs.AIresearchBeyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI
arXiv:2610.39230v1 Announce Type: new Abstract: Financial AI systems must support decision-bearing questions involving payments, collections, cash flow, and compliance while ensuring numerical accuracy, traceability, and…
- arXiv cs.AIresearchSocialArena: Evaluating Social Intelligence in Large Language Models
arXiv:2610.39247v1 Announce Type: new Abstract: We introduce SocialArena, a benchmark for systematically defining and evaluating the social intelligence of large language models (LLMs). Although LLMs are increasingly dep…
- arXiv cs.AIresearchLLM-Assisted Optimization for Simulation-Based Redesign
arXiv:2610.39275v1 Announce Type: new Abstract: Engineering design frequently involves redesigning a prior solution to adapt to changes in context, such as material prices or system requirements. Redesign often leverages…
- arXiv cs.AIresearchProving and Improving the Platonic Representation Hypothesis with JEPAs
arXiv:2610.39302v1 Announce Type: new Abstract: Whether models trained on different modalities converge to the same representation of the world is central to AI. The Platonic Representation Hypothesis (PRH) conjectures t…
- arXiv cs.AIresearchCoToan: Executable Rules and a Representation Contract for Reproducible Game AI Evaluation
arXiv:2610.39353v1 Announce Type: new Abstract: Game AI results are comparable only when different implementations expose the same decision problem. Yet seemingly minor representation choices can silently change that pro…
- arXiv cs.AIresearchRetaining Repair Hypotheses for Cost-Aware Execution
arXiv:2610.39410v1 Announce Type: new Abstract: Several corrections of an executable model can fit the same observations while predicting different execution outcomes. We study a repair-to-execution interface that retain…
- arXiv cs.AIresearchVerifiable LLM-Guided Focal SMT Solving for Quantified Arrays
arXiv:2610.39435v1 Announce Type: new Abstract: Large language models can often identify useful semantic structure in formal artifacts, but their outputs cannot be trusted as proofs or solver decisions. We study whether…
- arXiv cs.AIresearchTimbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning
arXiv:2610.39439v1 Announce Type: new Abstract: Label-free test-time reinforcement learning adapts vision--language models using rewards derived from their own predictions. However, misinterpreted visual evidence and sen…
- arXiv cs.AIresearchKairos: Semantics-Aware Orchestration of Planning Engines across Classical, Numeric, Temporal and Hybrid PDDL
arXiv:2610.39454v1 Announce Type: new Abstract: Planning at run time, as in robots that re-plan while they act, needs a planner that reads the PDDL its users write (durative actions, numeric resources, time windows, cont…
- arXiv cs.AIresearchDoes Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
arXiv:2610.39483v1 Announce Type: new Abstract: Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requires training on sensitive data from multiple organi…
- arXiv cs.AIresearchIntegrated Feature Selection for classification and Representation Learning with Group-Lasso Siamese Networks
arXiv:2610.39499v1 Announce Type: new Abstract: The Least Absolute Shrinkage and Selection Operator (Lasso) has been widely employed for feature selection in linear models and has also been extended to multi-layer percep…
- arXiv cs.AIresearchWhat Breaks When Facts Become Stories? The Distortions Source-Agreement Metrics Miss When Models Retell Real Events
arXiv:2610.39500v2 Announce Type: replace Abstract: Language models are now widely used to turn recorded facts into media for public consumption, yet evaluation of such output still assumes agreement with the source as i…
- arXiv cs.AIresearchDEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems
arXiv:2610.39512v1 Announce Type: new Abstract: Traditional neural solvers for solving vehicle routing problems (VRPs) often suffer from limited solution diversity, motivating the development of Generative Flow Network (…
- arXiv cs.AIresearchCategory-Anchored Large Language Models for Next POI Recommendation
arXiv:2610.39518v1 Announce Type: new Abstract: Next point-of-interest (POI) recommendation aims to predict a user's next destination from spatio-temporal check-in data, and serves as the foundation for many location-bas…
- arXiv cs.AIresearchNon-Zero Radius: The Missing Component of Neural Networks
arXiv:2610.39559v1 Announce Type: new Abstract: Inspired by the analogy between the all-or-none activation of biological neurons and the true-false of logic circuits, McCulloch and Pitts proposed a mathematical model of…
- arXiv cs.AIresearchEmergence of the transformer architecture as the score of entropic laws of random measures
arXiv:2610.39614v1 Announce Type: new Abstract: We show that the transformer architecture emerges as the score of last-token laws in a natural statistical model of language, where sentences are empirical measures of toke…
- arXiv cs.AIresearchFrom the Transformer to a Formal Semantics of Coordinated Transformations
arXiv:2610.39735v1 Announce Type: new Abstract: We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstr…
- arXiv cs.AIresearchPAPERBENCHX: Can AI Reproduce Science Across Disciplines?
arXiv:2610.39744v1 Announce Type: new Abstract: Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist…
- arXiv cs.AIresearchThe Role of Self-Concept In Language Models
arXiv:2610.39795v1 Announce Type: new Abstract: When a language model says "I," does it refer to its parameter weights, its currently running process, its stable preferences, its model lineage, or the goals it pursues? D…
- arXiv cs.AIresearchRevisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective
arXiv:2610.39802v1 Announce Type: new Abstract: Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Desp…
- arXiv cs.AIresearchAegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching
arXiv:2610.39825v1 Announce Type: new Abstract: Pretrained generative models, such as diffusion and flow matching models, have demonstrated exceptional capabilities in synthesizing high-quality data. However, steering th…
- arXiv cs.AIresearchEfficient Learning of Mechanism Designs and Compositionality
arXiv:2610.40005v1 Announce Type: new Abstract: Learning mechanism behaviour requires a representation of how connected parts jointly constrain motion. We study whether exposing reusable constraint subassemblies improves…
- arXiv cs.AIresearchCheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information
arXiv:2610.40030v1 Announce Type: new Abstract: Memory in reinforcement learning raises two problems. Attention finds the relevant item by scoring the whole store, which is costly for robots under latency and energy limi…
- arXiv cs.AIresearchReward-Adaptive Co-Evolution of Policy and Rubric
arXiv:2610.40096v1 Announce Type: new Abstract: Rubric-based rewards provide fine-grained, interpretable supervision for open-ended reinforcement learning, where holistic scalar rewards struggle to capture multidimension…
- arXiv cs.AIresearchThe generative paradox: the Anti-Prompt paradigm for human capability
arXiv:2610.40151v1 Announce Type: new Abstract: Generative AI in education is usually judged by the output of human-AI teams. That focus overlooks a second outcome: what people can still understand, challenge, repair, an…
- arXiv cs.AIresearchA Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery
arXiv:2610.40161v1 Announce Type: new Abstract: Increasingly, users express their needs as natural-language intents rather than structured requests. These intents may be incomplete, high-level, or internally conflicting.…
- arXiv cs.AIresearchBridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs
arXiv:2610.40192v1 Announce Type: new Abstract: Link prediction on text-attributed graphs (TAGs) is a fundamental problem with applications in knowledge discovery, recommendation and beyond. Recent progress has highlight…
- arXiv cs.AIresearchReaction precedents extend retrosynthetic prediction beyond training coverage
arXiv:2610.40249v1 Announce Type: new Abstract: Reaction precedents guide retrosynthesis, but how far they can compensate for gaps in task-specific training coverage remains unclear. Using 2.71 million reactions, we rest…
- arXiv cs.AIresearchDistributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR
arXiv:2610.40250v1 Announce Type: new Abstract: We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-lev…
- arXiv cs.AIresearchNeighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering
arXiv:2610.40278v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propaga…
- arXiv cs.AIresearchMultistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study
arXiv:2610.40330v1 Announce Type: new Abstract: As the effects of climate change become increasingly apparent, the demand for renewable energy sources such as wind power continues to grow. However, renewables' variable a…
- arXiv cs.AIresearchBeyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures
arXiv:2610.40382v1 Announce Type: new Abstract: The last year has seen a shift in AI-assisted mathematics, with frontier language models producing proofs of and counterexamples to long-standing open conjectures. However,…
- arXiv cs.AIresearchRetrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation
arXiv:2610.40409v1 Announce Type: new Abstract: Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain…
- arXiv cs.AIresearchTraining language models in simulation for psychiatric intake
arXiv:2610.40476v1 Announce Type: new Abstract: In psychiatric practice, the clinical intake interview remains a primary diagnostic instrument, requiring the clinician to establish rapport while disentangling complex, ov…
- arXiv cs.AIresearchAlgebraic World Model: From Exploration to Proofs
arXiv:2610.40503v2 Announce Type: replace Abstract: AI has made remarkable progress in mathematics, solving challenging problems with machine-checkable proofs in Lean, yet typically relying on predefined mathematical def…
- arXiv cs.AIresearchEfficient Scalable Oversight via Rewinding
arXiv:2610.40535v1 Announce Type: new Abstract: Scalable oversight asks how a weak verifier can check the outputs of computations performed by more powerful AI systems. One proposed approach uses relativizing interactive…
- arXiv cs.AIresearchOn the Fundamental Limits of Prefill-Based Decoding Length Prediction
arXiv:2610.40541v1 Announce Type: new Abstract: Predicting how many tokens a large language model (LLM) will decode, using only prefill-phase hidden states, is a key primitive for inference scheduling. We show that curre…
- arXiv cs.AIresearchRamanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs
arXiv:2610.40551v1 Announce Type: new Abstract: As AI's mathematical capabilities rapidly improve, meaningful benchmarks are shifting from university-level problems and math olympiads to research-level mathematics. The R…
- arXiv cs.AIresearchFARMS: A Verifiable Foundation for Automated Computational Science
arXiv:2610.40560v1 Announce Type: new Abstract: Automated computational science could accelerate discovery by selecting, adapting and developing numerical methods. This prospect requires mathematical knowledge that AI sy…
- arXiv cs.AIresearchComparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns
arXiv:2610.40563v1 Announce Type: new Abstract: This study investigates the capabilities of Large Language Models to simulate counselling clients in educational role-plays in comparison to human role-players. Initially,…
- arXiv cs.AIresearchLLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting
arXiv:2510.20952v1 Announce Type: cross Abstract: Forecasting in the real world requires integrating structured time-series data with unstructured textual information, but existing methods are architecturally limited by…
- arXiv cs.AIresearchArtifact Distillation: Training-Free Transfer from Frontier to Small Language Models
arXiv:2610.37680v1 Announce Type: cross Abstract: Closing the gap between frontier and smaller language models is usually approached by distillation: fine-tuning the small model (student) on a frontier model's (teacher)…
- arXiv cs.AIresearchSupervised Fine-Tuning for Reasoning Large Language Models: A Survey
arXiv:2610.37681v1 Announce Type: cross Abstract: Large reasoning models have recently demonstrated remarkable capabilities in solving complex tasks, where supervised fine-tuning (SFT) on long chain-of-thought data serve…
- arXiv cs.AIresearchRank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment
arXiv:2610.37682v1 Announce Type: cross Abstract: Listwise preference feedback offers richer supervision for large language model (LLMs) alignment than pairwise comparisons, but a full ranking also reveals more sensitive…
- arXiv cs.AIresearchPrompt-agnostic Language Models
arXiv:2610.37683v1 Announce Type: cross Abstract: Despite their strong performance, large language models remain highly sensitive to prompt formulation. This issue is typically addressed at inference-time through manual…
- arXiv cs.AIresearchAn Introduction to Large Language Models for Scientists and Professionals
arXiv:2610.37684v1 Announce Type: cross Abstract: Large Language Models (LLMs) have rapidly become important tools for science, education, medicine, and professional work. Despite their apparent simplicity from the user'…
- arXiv cs.AIresearchFrom Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs
arXiv:2610.37685v1 Announce Type: cross Abstract: Language models do not merely memorize facts; they absorb rhetorical strategies from pretraining data, including the human tendency to reason by analogy. We ask: is this…