AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsCertify the Decision, Not Every Score: Exact Top-k Selection from Few Evaluations
arXiv:2610.14996v1 Announce Type: new Abstract: Choosing a few robust algorithms or schedules can require evaluating every candidate under many adverse scenarios, even though an agent only needs to identify the winners.…
- arXiv cs.AIresearchCan You Trust Your Preference Models? Stackelberg Games for Alignment
arXiv:2610.15008v1 Announce Type: new Abstract: Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policies to search for comp…
- arXiv cs.AIresearchOn the Complexity Gap Between POMDPs and Multi-Environment POMDPs
arXiv:2610.15010v1 Announce Type: new Abstract: Multi-environment POMDPs (ME-POMDPs) generalize POMDPs by encoding a finite set of possible environments, capturing model uncertainty. The finite-horizon robust reward maxi…
- arXiv cs.AIagentsBelief Embedding Tree Search
arXiv:2610.15046v1 Announce Type: new Abstract: Beliefs in a Partially Observable Markov Decision Process (POMDP) are posterior distributions over the hidden state given the agent's history of actions and observations. T…
- arXiv cs.AIagentsTrace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces
arXiv:2610.15055v1 Announce Type: new Abstract: Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before. That difference can credit a frozen rescore as evolution. W…
- arXiv cs.AIresearchExposing AI Inference as a Telco Network API over the 5G User Plane
arXiv:2610.15062v1 Announce Type: new Abstract: Supporting edge Artificial Intelligence (AI) inference as a network service is challenging because current mobile systems can transport tensors but do not expose or underst…
- arXiv cs.AIresearchKnowledge transfer between simple discrete worlds
arXiv:2610.15081v1 Announce Type: new Abstract: Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying general intelligence. We…
- arXiv cs.AIagentsSelf-Evolving Visual Agent via Margin Reward
arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool invocation usually reli…
- arXiv cs.AIresearchStructural Chain-of-Thought: Reasoning with Executable Computational Graphs
arXiv:2610.15107v1 Announce Type: new Abstract: Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful…
- arXiv cs.AIresearchGesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?
arXiv:2610.15129v1 Announce Type: new Abstract: Human social perception is incremental: we infer intent before an utterance is complete, revise our interpretation as new cues arrive, and attend to specific facial, gestur…
- arXiv cs.AIresearchTrust Hinders Bidirectional Human-AI Alignment
arXiv:2610.15136v2 Announce Type: replace Abstract: Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthiness of AI systems s…
- arXiv cs.AIresearchSingle-step Retrosynthesis via Reinforcement Learning from Forward Feedback
arXiv:2610.15141v1 Announce Type: new Abstract: Single-step retrosynthesis is a one-to-many inverse problem, yet most models are trained and evaluated against a single recorded reactant set. Reference-based training give…
- arXiv cs.AIagentsHarmony Harness: Multi-Objective Self-Evolution of Agent Harnesses
arXiv:2610.15150v1 Announce Type: new Abstract: Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches,…
- arXiv cs.AIagentsCan agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments
arXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is in force from the fir…
- arXiv cs.AIresearchContinuous Risk-Based Scheduling for Food Safety Inspection: Integrating Historical Decay with Event-Driven Consumer Review Signals
arXiv:2610.15191v1 Announce Type: new Abstract: Batch risk-based inspection scheduling struggles to detect a critical failure class: food facilities with recent clean inspections that subsequently develop severe violatio…
- arXiv cs.AIresearchSocraticRepair: Planning-Guided Socratic Tutoring for Program Debugging and Misconception Repair
arXiv:2610.15204v1 Announce Type: new Abstract: Large language models are increasingly used in computer science education. However, the teaching abilities of even the most powerful LLMs are limited: they tend to reveal t…
- arXiv cs.AIresearchRunning Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the model runs, not when…
- arXiv cs.AIagentsHarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems
arXiv:2610.15221v1 Announce Type: new Abstract: AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation…
- arXiv cs.AIresearchUnderstanding Unified VLMs: From Attention Probing to Guidance Tuning for Multimodal Generation
arXiv:2610.15227v1 Announce Type: new Abstract: Unified vision-language models (VLMs) perform both text-to-image (T2I) and image-to-text (I2T) generation with one shared Transformer backbone, yet how the backbone process…
- arXiv cs.AIresearchWords to World: Benchmarking LLMs in Interactive Physical Environments
arXiv:2610.15228v1 Announce Type: new Abstract: Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that affect the physical wor…
- arXiv cs.AIresearchUsing Evidence-Centered Design to Guide Prompt Engineering in Measurement: An Illustration with Automated Essay Scoring
arXiv:2610.15231v2 Announce Type: replace Abstract: Generative artificial intelligence (GenAI) models, particularly large language models (LLMs), are increasingly used in educational settings for tasks such as item gener…
- arXiv cs.AIresearchMoMaTune: Model, Match, Then Tune Language Models for Numerical Records
arXiv:2610.15235v1 Announce Type: new Abstract: Despite remarkable progress in language understanding and generation, decoder language models continue to exhibit striking failures on numerical data. Numerical examples ar…
- arXiv cs.AIresearchClinEdge: An Expert-Graded Benchmark of Real Patient Edge Cases Where Frontier Multimodal Models Fail
arXiv:2610.15239v1 Announce Type: new Abstract: Most benchmarks for large language models in medicine are built from licensing examinations and theoretical questions. The few that draw on real clinical data do so only in…
- arXiv cs.AIresearchRECAP: Calibrating Low-Bit Reasoning Models on the History They Read
arXiv:2610.15259v1 Announce Type: new Abstract: Low-bit quantization reduces the cost of serving reasoning models but can substantially degrade long chains of thought. Each step reads cached keys and values spanning thou…
- arXiv cs.AIagentsOntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition
arXiv:2610.15292v1 Announce Type: new Abstract: LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge. Retrieval-augmented genera…
- arXiv cs.AIresearchCHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition
arXiv:2610.15298v1 Announce Type: new Abstract: Large language models (LLMs) offer a new approach to wearable-sensor-based human activity recognition. Retrieval-augmented generation (RAG) further introduces similar motio…
- arXiv cs.AIresearchSuperAI: Merging Capabilities Across Heterogeneous Foundation Models
arXiv:2610.15322v2 Announce Type: replace Abstract: Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable artificial intellige…
- arXiv cs.AIresearchMultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching
arXiv:2610.15339v1 Announce Type: new Abstract: Current fMRI encoding models frame prediction as deterministic regression, yet identical stimuli evoke a distribution of neural responses (arising from physiological noise,…
- arXiv cs.AIresearchTRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation
arXiv:2610.15365v1 Announce Type: new Abstract: Large language models (LLMs) can produce harmful content while generating a response. A useful safeguard should not only detect this risk during generation but also interve…
- arXiv cs.AIresearchFewer Bits, More Tries: Recovering Capability Under Memory Constraints
arXiv:2610.15372v1 Announce Type: new Abstract: Large language models are generally more capable than smaller ones, but their memory requirements can make local deployment difficult. We ask whether part of this capabilit…
- arXiv cs.AIresearchAnalyzing the Dynamics of WSBM-based Echo State Networks using InputDSA
arXiv:2610.15380v1 Announce Type: new Abstract: Bridging the structural gap between biological brains and artificial neural networks presents a pathway to altered computational dynamics. This paper introduces a Reservoir…
- arXiv cs.AIresearchA Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning
arXiv:2610.15403v1 Announce Type: new Abstract: Crowdsourced disaster imagery provides timely, ground-level observations when conventional disaster mapping is delayed or incomplete, yet its geographic value depends on wh…
- arXiv cs.AIagentsState Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study
arXiv:2610.15407v1 Announce Type: new Abstract: An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes. We study this distinction in deterministic to…
- arXiv cs.AIagentsCoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets
arXiv:2610.15409v1 Announce Type: new Abstract: Enterprise agents need retrieval evaluation sets that expose domain-specific failures and guide developers towards efficient deployment tradeoffs. Neither expert-human-auth…
- arXiv cs.AIresearchSpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference
arXiv:2610.15417v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D) expert transfers ent…
- arXiv cs.AIresearchHidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play
arXiv:2610.15449v2 Announce Type: replace Abstract: Despite significant advances in language understanding, Large Language Models (LLMs) can still miss meaning hidden in plain sight, failing to identify harmful intent in…
- arXiv cs.AIresearchScalable Robust MCTS with Anytime Deterministic Optimality Guarantees
arXiv:2610.15461v1 Announce Type: new Abstract: MDP planners often rely on nominal transition models that may differ from the true dynamics. Robust MDP planning accounts for this uncertainty through a set of admissible m…
- arXiv cs.AIresearchMemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection
arXiv:2610.15463v2 Announce Type: replace Abstract: With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through co…
- arXiv cs.AIagentsSkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents
arXiv:2610.15481v1 Announce Type: new Abstract: Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM agent. We propose SkillF…
- arXiv cs.AIagentsWhen Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization
arXiv:2610.15492v1 Announce Type: new Abstract: Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execute them without retr…
- arXiv cs.AIresearchLarge Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers
arXiv:2610.15501v1 Announce Type: new Abstract: Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does not explicitly expos…
- arXiv cs.AIresearchData Portability Revisited: Toward the Human-Centric, AI-Driven Data Ecosystems of Tomorrow
arXiv:2610.15503v1 Announce Type: new Abstract: This Article critically examines the contemporary regulatory framework and discourse surrounding data portability in the United States. Using recent regulatory developments…
- arXiv cs.AIagentsAgent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems
arXiv:2610.15529v2 Announce Type: replace Abstract: Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected b…
- arXiv cs.AIresearchSelf-Representation Alignment in Diffusion Models for Video Background Music Generation
arXiv:2610.15575v1 Announce Type: new Abstract: Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned in the diffusion mo…
- arXiv cs.AIagentsInverse Garment Design with Visual Agents
arXiv:2610.15582v1 Announce Type: new Abstract: We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual agents. Unlike differentia…
- arXiv cs.AIresearchCondMSP: Condition-Informed and Resource-Aware Inorganic Materials Synthesis Planning
arXiv:2610.15603v1 Announce Type: new Abstract: Materials synthesis planning (MSP) connects AI-driven materials discovery to experimental realization by proposing precursors, synthesis operations, and processing conditio…
- arXiv cs.AIresearchFrom Stages to States: Unified Iterative Reasoning for MLLMs
arXiv:2610.15620v2 Announce Type: replace Abstract: Multimodal Chain-of-Thought (MCoT) substantially enhances the complex reasoning capabilities of Multimodal Large Language Models (MLLMs) by explicitly modeling intermed…
- arXiv cs.AIresearchBig-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribute to research synth…
- arXiv cs.AIagentsRecall What Is Missing: Composing Evidence from Long-Term Agent Memory
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively sufficient for the curre…
- arXiv cs.AIresearchKnowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition
arXiv:2610.15677v1 Announce Type: new Abstract: Continual learning aims to adapt pretrained large language models (LLMs) to evolving data while preserving their pretrained capabilities. A central challenge is catastrophi…