AI news archive.
19,856 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDiRAFT: Privacy-Aware Financial Transcript Synthesis from Aggregate Discourse Priors
arXiv:2610.40938v1 Announce Type: new Abstract: Using customer conversations to train and evaluate financial language models raises confidentiality concerns because non-public financial facts can remain after direct iden…
- arXiv cs.AIagentsThe First Few Tokens Matter: Understanding Chain-of-Thought Controllability
arXiv:2610.40939v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising way to oversee increasingly capable agents. It succeeds in part because current models appear limited in their ability to c…
- arXiv cs.AIagentsBenchmarking Forecasting Agents on Yesterday's Tomorrows
arXiv:2610.40940v1 Announce Type: new Abstract: Digital agents can now gather and organize information, reason over it, and use tools to complete complex tasks. Forecasting puts all of these abilities to the test: it req…
- arXiv cs.AIresearchOpening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?
arXiv:2610.40946v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning allows large language models (LLMs) to generate intermediate reasoning traces in natural language while solving complex tasks. These traces…
- arXiv cs.AIagentsP-ContextBench: From Personal Fact Recall to Personalized Agent Behavior
arXiv:2610.40959v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for personal tasks, yet evaluating their safe use of personal context remains difficult because such contexts are private…
- arXiv cs.AIresearchNedimo: An Evidence-Grounded Multilingual Pipeline for AI-Generated Sleep Stories
arXiv:2610.40970v1 Announce Type: new Abstract: Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives (retention, completion, and novelty) are poorly aligned…
- arXiv cs.AIagentsThe psychophysics of affect in large language models
arXiv:2610.40985v1 Announce Type: new Abstract: Good decisions often require considering how outcomes will feel. Yet large language models (LLMs) increasingly enter decision workflows, despite little being known about ho…
- arXiv cs.AIresearchCan Personal Requirements Become Supervision for Planning?
arXiv:2610.40992v1 Announce Type: new Abstract: Managing multiple chronic conditions through diet requires satisfying disease- and medication-specific requirements jointly across meals and days while preserving establish…
- arXiv cs.AIresearchViolet Teaming in Practice: Lessons from a Pilot Expert Workshop on Governing Complex AI Systems
arXiv:2610.41018v1 Announce Type: new Abstract: Violet teaming has been proposed as a method to integrate technical, policy, and societal considerations into the evaluation of emerging technologies. Here, we document a p…
- arXiv cs.AIagentsReplayRCA: Measuring Post-hoc Diagnosis and Live Oversight of Agent Failures by Counterfactual Replay
arXiv:2610.41025v1 Announce Type: new Abstract: When a language-model agent fails a multi-step task, can another model find the decisive mistake and fix it with a single action? We introduce ReplayRCA, a benchmark that s…
- arXiv cs.AIagentsCapability-Grounded Agentic Planning
arXiv:2610.41040v1 Announce Type: new Abstract: LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the L…
- arXiv cs.AIagentsConsensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense
arXiv:2610.41044v1 Announce Type: new Abstract: The use of large language models (LLMs) to coordinate multi-agent teams raises a fundamental architectural question: whether task allocation should be centralized in a sing…
- arXiv cs.AIagentsLanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale
arXiv:2610.41072v1 Announce Type: new Abstract: Security operations centers (SOCs) need to turn terabytes of alerts, logs and flows into trusted, affordable decisions to unveil hidden threats. We present LanG 2.0, an age…
- arXiv cs.AIagentsBABA-Bench: Evaluating Long-Horizon Patient-Advocacy Agents
arXiv:2610.41076v1 Announce Type: new Abstract: An LLM agent that helps a patient get care must do two things. It must reach the correct outcome, and it must follow the necessary procedure. For example, the agent must ge…
- arXiv cs.AIresearchOptimization Techniques for Solving the Minimum Red--Blue Separating Set Problem with an Application to Human--AI Text Separation
arXiv:2610.41081v1 Announce Type: new Abstract: We study the so-called Minimum Red''Blue Separating Set Problem (MRBSSP) which arises from computational geometry. In particular, we propose a compact Set-Cover ILP formula…
- arXiv cs.AIresearchPayroll Fraud Detection in Synthetic HR/ERP Graphs: An Inductive Comparison of Rules, Path Features, and Graph Neural Networks
arXiv:2610.41085v1 Announce Type: new Abstract: Payroll-fraud screening requires finding hidden employee--payee links while distinguishing suspicious relationships from legitimate ones. We formulate this problem as induc…
- arXiv cs.AIresearchCIRCE Divines LLM Task Complexity from Constraint Structure
arXiv:2610.41089v1 Announce Type: new Abstract: Estimating whether a problem is too complex for a large language model (LLM) before the model attempts it can guide model routing, how to allocate test-time compute, and su…
- arXiv cs.AIagentsVerifying Text-to-SQL Queries under Changing Business Semantics
arXiv:2610.41090v1 Announce Type: new Abstract: In text-to-SQL and AI-agent analytics, successful SQL execution does not establish semantic correctness under changing business definitions. We study revalidation of fixed…
- arXiv cs.AIresearchQUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models
arXiv:2610.41100v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) provide zero-shot forecasts for unseen series, but their accuracy varies across datasets. Combining several models can reduce this var…
- arXiv cs.AIresearchDifferential rank preservation manifold learning
arXiv:2610.41107v1 Announce Type: new Abstract: Manifold learning methods like t-SNE and UMAP preserve local neighborhoods, but they do not preserve the ranking of the neighbors inside them. Two embeddings can return the…
- arXiv cs.AIresearchCalibration of Large Model Quantization based on HiFloat4 Format
arXiv:2610.41112v1 Announce Type: new Abstract: Quantization of Large Language Models (LLMs) has be- coming increasingly important for reducing the computa- tional costs and resource requirements for practical deploy- me…
- arXiv cs.AIresearchPredicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings
arXiv:2610.41114v1 Announce Type: new Abstract: Optimizing a proxy objective can improve human-perceived quality, but the resulting gain can vary with optimization strength. Average proxy-human correlation alone does not…
- arXiv cs.AIagentsConfident Fools or Careful Searchers? A Behavioural Study of When LLMs Search Beyond Their Static Internal Memory
arXiv:2610.41124v1 Announce Type: new Abstract: Agentic LLM assistants must repeatedly decide whether to answer from memory or to call a tool such as web search. Unnecessary searches cost latency and money; missing ones…
- arXiv cs.AIagentsWhen Should AI Agents Ask? Clarification Requests Under Limited Human Attention
arXiv:2610.41129v1 Announce Type: new Abstract: AI agents increasingly carry out delegated tasks in parallel, with one person overseeing several of them at once. In practice, an agent often lacks information its task req…
- arXiv cs.AIagentsCounterfactual Pairwise Augmentation Improves Small Pointwise LLM Judges
arXiv:2610.41149v1 Announce Type: new Abstract: Agentic systems increasingly gate individual steps with a pointwise judge that scores a response against a criterion. Small language models are attractive for this role bec…
- arXiv cs.AIresearchLifelong Learning of Scheduling Rules with Surrogate-assisted Genetic Programming for Dynamic Flexible Job Shop Scheduling
arXiv:2610.41158v1 Announce Type: new Abstract: Genetic programming (GP) has been widely used to learn scheduling rules for dynamic flexible job shop scheduling (DFJSS). However, trained rules tend to only generalise to…
- arXiv cs.AIresearchFrontierMat: Benchmarking Language Models at the Frontier of Materials R&D
arXiv:2610.41162v1 Announce Type: new Abstract: To accelerate materials discovery, language models must be able to address problems at the research frontier. Yet textbook- and examination-derived benchmarks primarily ass…
- arXiv cs.AIresearchLLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
arXiv:2610.41165v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate toxic content, motivating effective test-time detoxification. Existing representation steering methods often rely on static or coa…
- arXiv cs.AIresearchImplicitHop: Evaluating knowledge integration across context and memory
arXiv:2610.41169v1 Announce Type: new Abstract: The ability to integrate new information and deduce its consequences is central to learning, understanding, and reasoning in large language models (LLMs). Whether informati…
- arXiv cs.AIresearchResearcher-in-the-Loop Evolutionary Discovery of Entanglement-Assisted Quantum Code Families
arXiv:2610.41183v1 Announce Type: new Abstract: LLM-guided program evolution can produce mathematical constructions, but validity, generality, and reproducibility require distinct evidence. We develop a researcher-in-the…
- arXiv cs.AIresearchRTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design
arXiv:2610.41225v1 Announce Type: new Abstract: Large language models offer a promising route to register-transfer-level (RTL) design, but reliable implementations require checking and revision based on electronic design…
- arXiv cs.AIresearchTRIDENT and SHAKTI: A Framework and Benchmark for Hindi AI-Text Detection
arXiv:2610.41232v1 Announce Type: new Abstract: As Large Language Models (LLMs) become increasingly multilingual, distinguishing human-written from AI-generated text is essential for maintaining information integrity. Ho…
- arXiv cs.AIresearchExperts Exhibit Structured Redundancy: Structure-Preserving Expert Pruning for Mixture-of-Experts Large Language Models
arXiv:2610.41236v1 Announce Type: new Abstract: Sparse MoE mechanism significantly improves the trade-off between model capacity and inference efficiency. However, practical deployment still requires storing all experts,…
- arXiv cs.AIagentsMEMIG: Self-evolving Memory Construction for Antibody Optimization
arXiv:2610.41245v1 Announce Type: new Abstract: Memory has become central to self-evolving LLM agents, which store and retrieve experience from past rollouts to guide future decisions. Existing systems represent this exp…
- arXiv cs.AIagentsRome Wasn't Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents
arXiv:2610.41264v1 Announce Type: new Abstract: Training language-model agents to play long-horizon strategy games is hard because deterministic feedback is sparse and often arrives only at the end of a game. In-game sco…
- arXiv cs.AIagentsFrom 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation?
arXiv:2610.41267v1 Announce Type: new Abstract: Turning an engineering request into a simulation requires consistent geometry, physics, boundary conditions, and numerical settings. Recent agent-assisted systems automate…
- arXiv cs.AIresearchSciGraphSelect: Auditable Scientific Data Selection through Knowledge--Reasoning Graphs
arXiv:2610.41280v1 Announce Type: new Abstract: Scientific data selection is typically driven by relevance or utility scores, providing limited insight into why a document is retained. We introduce SciGraphSelect, a refe…
- arXiv cs.AIresearchSAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences
arXiv:2610.41290v1 Announce Type: new Abstract: Learning-based approaches have increasingly been explored for SAT solving, with particular attention to improving branching decisions in conflict-driven clause learning (CD…
- arXiv cs.AIresearchSelf-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer
arXiv:2610.41296v1 Announce Type: new Abstract: Answer-level rewards cannot distinguish reasoning traces with equally correct outcomes. We study whether auxiliary trajectory preferences improve small-language-model self-…
- arXiv cs.AIresearchSubliminal Reinforcement Learning: traits travel through a judge's scores
arXiv:2610.41301v1 Announce Type: new Abstract: Subliminal learning, the transfer of a model's trait through data with no semantic trace of it, has been shown for students trained on a teacher's text. Post-training relie…
- arXiv cs.AIresearchSERIAL-7: Deriving, Realizing, and Preserving Machine-Verifiable Outputs Across Representations
arXiv:2610.41308v1 Announce Type: new Abstract: Large language models increasingly generate structured outputs consumed by programs and downstream systems, where semantic correctness alone does not guarantee reliable exe…
- arXiv cs.AIagentsOperon-S1: a fast decision controller for long-horizon biomedical agents
arXiv:2610.41350v1 Announce Type: new Abstract: Language-model agents now carry out long scientific work in biology, but their judgements about conventions, skills, errors, evidence and stopping are made inside the reaso…
- arXiv cs.AIresearchDo Transaction Prices Reflect Visual Preference? A Diagnostic Study with Multimodal Language Models
arXiv:2610.41358v1 Announce Type: new Abstract: Existing visual preference evaluation relies on costly human annotations or preference reward models, whereas online marketplace transaction prices are readily available an…
- arXiv cs.AIresearchLEAP: Efficient LLM Inference Scheduling with Generalizable Length Prediction
arXiv:2610.41359v1 Announce Type: new Abstract: Length-aware scheduling reduces request latency in LLM serving by prioritizing shorter requests. However, despite their large model sizes, length predictors can suffer degr…
- arXiv cs.AIresearchRECITE: Revising Eligibility Criteria Incorporating Textual Evidence
arXiv:2610.41368v1 Announce Type: new Abstract: Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific criteria should be br…
- arXiv cs.AIresearchFrom the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings
arXiv:2610.41375v1 Announce Type: new Abstract: Choosing among the hundreds of thousands of available large language models (LLMs) requires a thorough understanding of each candidate model's properties. In practice, each…
- arXiv cs.AIagentsAsk on Demand: Targeted Peer Communication for Parallel Agentic Systems
arXiv:2610.41378v1 Announce Type: new Abstract: Parallel LLM agents tackle complex tasks by exploring multiple trajectories, yet useful discoveries remain isolated in individual execution histories. Existing sharing meth…
- arXiv cs.AIresearchOnline Evidence-Containment Prediction over Text Spans under Distinct Queries
arXiv:2610.41384v1 Announce Type: new Abstract: Evidence-grounded NLP systems often verify nested text regions sequentially, so verifying one region constrains others. We formalize this as Online Evidence-Containment Pre…
- arXiv cs.AIagentsCross-Interface Authorization for AI Computer-Use Agents
arXiv:2610.41397v1 Announce Type: new Abstract: Computer-use agents act through graphical interfaces, command lines, APIs, scripts, and Model Context Protocol servers. A policy decision can be interface-invariant while i…
- arXiv cs.AIresearchscAnyOmics: Foundation-Model Distillation for Any-to-Any Completion of Multi-omics Virtual Cells
arXiv:2610.41399v1 Announce Type: new Abstract: Recent advances in single-cell technologies have enabled the profiling of multiple molecular modalities, including transcriptomics, proteomics, and chromatin accessibility,…