AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation
arXiv:2610.04691v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is typically evaluated under the implicit assumption that the underlying knowledge base (KB) is clean, leaving the behaviour of RAG sys…
- arXiv cs.AIresearchPyINE: A Framework for Scalable Elicitation and Oversight via Code Execution
arXiv:2610.04737v2 Announce Type: replace Abstract: Reasoning models can remain capable of solving a task while still defaulting to cheaper but misleading shortcuts. This creates a central oversight problem: when a model…
- arXiv cs.AIresearchFormalizing the Moral Evaluation of Speech Acts: Truthfulness, Lies and Ethical Dilemmas
arXiv:2610.04747v1 Announce Type: new Abstract: In life-or-death situations, a benevolent lie may appear more moral than telling the truth. Yet such lies can backfire, producing unintended and sometimes fatal consequence…
- arXiv cs.AIresearchDynamic Routing as a New Dimension for Test-time Versatility of LLMs
arXiv:2610.04751v1 Announce Type: new Abstract: Beyond scaling their parameters and data, large language models currently gain versatility on new problems along a single axis: the tokens they spend on chain-of-thought (C…
- arXiv cs.AIresearchWhen Is Enough Enough in Self-Evolving LLM Systems?
arXiv:2610.04756v1 Announce Type: new Abstract: Self-evolving large language model (LLM) systems repeatedly propose, evaluate, and incorporate updates to prompts, skills, or other persistent artifacts. Despite their grow…
- arXiv cs.AIresearchNot All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
arXiv:2610.04791v1 Announce Type: new Abstract: At the core of modern prompting techniques is contextual sensitivity, the ability of large language models to adapt their predictions based on inference-time context. Despi…
- arXiv cs.AIresearchDo More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness
arXiv:2610.04792v2 Announce Type: replace Abstract: Missing modality remains a longstanding challenge in multimodal learning. Existing methods typically address this issue through modality recovery or adaptive strategies…
- arXiv cs.AIresearchDICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
arXiv:2610.04825v1 Announce Type: new Abstract: Fluent guidance is not the same as useful intervention. LLM tutors are typically trained to generate the next teacher utterance, implicitly assuming that every student turn…
- arXiv cs.AIresearchGitSwarm: Decentralized Compounding Inference
arXiv:2610.04862v1 Announce Type: new Abstract: Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental findings, and unsuccessfu…
- arXiv cs.AIresearchSpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
arXiv:2610.04875v2 Announce Type: replace Abstract: Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a m…
- arXiv cs.AIresearchMonitorability Disposition in Large Reasoning Models
arXiv:2610.04914v1 Announce Type: new Abstract: Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current monitoring is passive:…
- arXiv cs.AIresearchZero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning
arXiv:2610.04942v1 Announce Type: new Abstract: Time-series question answering (TSQA) requires grounding linguistic queries and diverse answer formats in complex numerical observations. However, existing methods heavily…
- arXiv cs.AIresearchEmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models
arXiv:2610.04998v1 Announce Type: new Abstract: Emotional expression can influence the safety decisions of large language models (LLMs), offering a potential avenue for improving safety alignment. Existing studies have m…
- arXiv cs.AIresearchCI-JEPA: A Counterfactual Analysis of Latent Representations in Joint-Embedding Predictive Architectures for Self-Supervised Learning
arXiv:2610.05043v1 Announce Type: new Abstract: Self-supervised visual representation learning learns useful features without manual annotations during representation training. The image-based joint-embedding predictive…
- arXiv cs.AIresearchWhy, Where, How: Taxonomy-guided Error Grounding for Code Repair in NL2SQL
arXiv:2610.05060v1 Announce Type: new Abstract: SQL queries that large language models write from natural language questions can execute successfully yet produce incorrect results, so execution alone does not reveal what…
- arXiv cs.AIresearchSharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling
arXiv:2610.05106v1 Announce Type: new Abstract: Long-form reasoning makes inference expensive, and speculative decoding mitigates this cost by verifying multiple draft tokens in parallel. Its speedup, however, can fade a…
- arXiv cs.AIresearchR1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments
arXiv:2610.05144v1 Announce Type: new Abstract: Recovering three-dimensional human geometry from electromagnetic measure?ments in a complex static environment is difficult because strong multipath responses from walls, f…
- arXiv cs.AIresearchBeyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts
arXiv:2610.05161v1 Announce Type: new Abstract: Instruction following typically enforces discrete, response-level requirements, whereas an expert-authored skill prescribes procedural requirements spanning multiple phases…
- arXiv cs.AIresearchA Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
arXiv:2610.05166v2 Announce Type: replace Abstract: A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to…
- arXiv cs.AIresearchCreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation
arXiv:2610.05167v1 Announce Type: new Abstract: Inspired by cognitive science, we present CREATIVEFLOW, an analogical generation framework that explicitly models analogical divergent thinking to mitigate creative homogen…
- arXiv cs.AIresearchImage Synthesis as an Intermediate for Controllable Time Series Generation
arXiv:2610.05211v1 Announce Type: new Abstract: Semantic-driven time-series generation offers a promising way to improve downstream learning in few-shot forecasting, but directly generating numerical sequences from langu…
- arXiv cs.AIresearchGFGE: Unifying Explainable AI Methods through an Interpretation Framework
arXiv:2610.05225v1 Announce Type: new Abstract: Explainable artificial intelligence (XAI) encompasses methods that draw on different sources of information and address different explanatory needs. A common framework is n…
- arXiv cs.AIresearchLearning from imperfect teachers for low-resource acoustic generalization
arXiv:2610.05256v1 Announce Type: new Abstract: Knowledge distillation (KD) improves low-resource acoustic learning by enriching one-hot supervision with the softened predictive distribution of a fixed teacher network. H…
- arXiv cs.AIresearchEnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans
arXiv:2610.05370v2 Announce Type: replace Abstract: Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments…
- arXiv cs.AIresearchLearning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimates
arXiv:2610.05375v2 Announce Type: replace Abstract: Reconstructing physical fields from training samples that are always incomplete requires learning spatial structure from fragmented observations. Existing context--quer…
- arXiv cs.AIresearchAI Safety via Debate is Compromised by Cognitive Biases
arXiv:2610.05461v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) has played a central role in making large language models responsive to human instructions. However, human evaluators ofte…
- arXiv cs.AIresearchHallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
arXiv:2610.05472v1 Announce Type: new Abstract: Reasoning errors can propagate into later decisions and memory. This survey synthesizes 312 papers and first-party reports on text-based reasoning hallucinations around thr…
- arXiv cs.AIresearchSkillGATE: Gate-Aware Monte Carlo Tree Search for Skill Retrieval
arXiv:2610.05489v1 Announce Type: new Abstract: Skill Retrieval (SR) aims to identify the most relevant skills from external skill libraries, and becomes increasingly challenging as libraries grow in scale and diversity.…
- arXiv cs.AIresearchThe Functional Structure of Post-Compression Recovery in Low-Rank LLMs
arXiv:2610.05504v1 Announce Type: new Abstract: Different low-rank compression methods can produce compressed LLMs that respond differently to the same post-compression recovery procedure, and relative advantages observe…
- arXiv cs.AIresearchWhat Does Fr\'echet Distance Measure? A Directional Decomposition
arXiv:2610.05518v1 Announce Type: new Abstract: The Fr\'echet distance is a de facto standard for evaluating generative models across domains, appearing as FID for images and FVD for videos. It summarizes the discrepancy…
- arXiv cs.AIresearchMore Claims, Less Evidence: Bounded Verification of AI-Generated Digital Knowledge Artifacts
arXiv:2610.05547v1 Announce Type: new Abstract: Digital libraries, repositories, and AI-mediated knowledge services increasingly rely on generative systems to produce summaries, descriptions, and other multi-claim knowle…
- arXiv cs.AIresearchBetter Retrieval, Limited Clustering Gains: A Controlled Study of Multilingual Company Entity Resolution
arXiv:2610.05573v2 Announce Type: replace Abstract: Company name retrieval and final entity clustering can respond differently to encoder adaptation. We study this dependency through a controlled pipeline: train multilin…
- arXiv cs.AIresearchThe GenAI4IDN Benchmark 3.0 - a Public Tool to Assess Generative AI Tools for the Design of Interactive Digital Narratives
arXiv:2610.05633v1 Announce Type: new Abstract: This paper presents GENAI4IDN Benchmark 3.0, the third iteration of an evaluation framework to assess Generative AI tools for creating Interactive Digital Narratives (IDNs)…
- arXiv cs.AIresearchHow Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation
arXiv:2610.05671v3 Announce Type: replace Abstract: Automatic prompt optimization (APO) has been widely employed to adapt large language models without updating their weights, yielding promising results. However, existin…
- arXiv cs.AIresearchDo Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability
arXiv:2610.05686v1 Announce Type: new Abstract: In recent years, time-series question answering (QA) systems have made significant progress. However, generating a correct answer does not show whether retaining the suppli…
- arXiv cs.AIresearchToward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems
arXiv:2610.05689v1 Announce Type: new Abstract: Neural-network (NN) controllers are increasingly used in nonlinear control systems, but their highly nonlinear behavior makes them difficult to explain and verify, raising…
- arXiv cs.AIresearchFrom Token-Max to Outcome-Max: How You Use AI Determines Its Productivity
arXiv:2610.05697v1 Announce Type: new Abstract: Generative artificial intelligence (AI) models can perform increasingly complex tasks, yet greater AI usage does not necessarily translate into proportional productivity ga…
- arXiv cs.AIresearchFreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis
arXiv:2610.05726v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong potential in multivariate time series forecasting and anomaly detection. Existing studies predominantly inject temporal infor…
- arXiv cs.AIresearchA Testable Theory of Atomic Features
arXiv:2610.05794v1 Announce Type: new Abstract: We develop and test a theory of language model representations in which there exist atomic features. Our main theoretical insight is that in such a model, sparse dictionari…
- arXiv cs.AIresearchDiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
arXiv:2610.05808v2 Announce Type: replace Abstract: Scientific design often requires jointly satisfying multiple objectives and constraints. Pretrained masked diffusion models provide a generative foundation for this tas…
- arXiv cs.AIresearchNash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation
arXiv:2610.05817v1 Announce Type: new Abstract: Text revision has become an integral component of large language models. This paper formulates revision such that it admits a Nash equilibrium: Token positions are players,…
- arXiv cs.AIresearchData-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes
arXiv:2610.05828v2 Announce Type: replace Abstract: Large language models (LLMs) offer new opportunities for public opinion research by enabling early prediction of survey responses, potentially reducing the cost and tim…
- arXiv cs.AIresearchGrounded Joint-Attention Other-Play for Zero-Shot Coordination
arXiv:2610.06025v1 Announce Type: new Abstract: Joint attention - the human ability to share a common visual or cognitive focus with others - enables a meeting of minds that lets us coordinate even with unfamiliar partne…
- arXiv cs.AIresearchOn Impact of Loss Function on the Performance of Neural Networks in Melanoma Diagnosis
arXiv:2610.06139v1 Announce Type: new Abstract: Melanoma is the deadliest type of skin cancer, whose early diagnosis is crucial for patients' survival. Image classification using deep learning models has shown promising…
- arXiv cs.AIresearchImpact of Data Augmentation on Confidence Calibration in Melanoma Classification
arXiv:2610.06146v1 Announce Type: new Abstract: Accurately quantifying the predictive uncertainty or improving model calibration plays an important role in medical image classification, in particular in melanoma diagnosi…
- arXiv cs.AIresearchMS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge
arXiv:2610.06170v2 Announce Type: replace Abstract: Biomedical large language model (LLM) evaluation requires auditable assessment of narrow, evolving, source-grounded subspecialty knowledge. Multiple sclerosis MRI (MS-M…
- arXiv cs.AIresearchAuditable Clinical Timeline Reconstruction with Provenance-Aware Evidence Graphs
arXiv:2610.06177v1 Announce Type: new Abstract: A patient-timeline reconstruction system is auditable only if it keeps the mentions behind each answer, records how facts were revised, and declines to answer when the evid…
- arXiv cs.AIresearchFrom Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models
arXiv:2610.06248v1 Announce Type: new Abstract: Scientific language models often access literature through untyped text chunks, which fragment the functional and evidential structure required for mechanism-rich questions…
- arXiv cs.AIresearchEvolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries
arXiv:2610.06269v2 Announce Type: replace Abstract: Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and ref…
- arXiv cs.AIresearchDPNL: A DPLL-based Algorithm for Probabilistic Neurosymbolic Learning
arXiv:2610.06270v1 Announce Type: new Abstract: Probabilistic Neurosymbolic Learning (PNL) combines neural predictions with symbolic reasoning, enabling end-to-end learning from final-output supervision without labels fo…