AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRadioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision
arXiv:2610.15685v1 Announce Type: new Abstract: Conventional distillation transfers capability through teacher-generated demonstrations. LLM-as-a-Judge knowledge distillation offers a distinct and increasingly practical…
- arXiv cs.AIresearchFARL: A Fully Automated Pipeline of RL Interface and Solver Design
arXiv:2610.15691v1 Announce Type: new Abstract: Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies he…
- arXiv cs.AIagentsSpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications
arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weights. We study recursiv…
- arXiv cs.AIagentsSuggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate
arXiv:2610.15710v1 Announce Type: new Abstract: Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair as changed or not, so…
- arXiv cs.AIagentsMedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation
arXiv:2610.15714v1 Announce Type: new Abstract: Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions under which model-centr…
- arXiv cs.AIresearchHistory Replays Itself: Unleashing Long-Context Capability in Linear Attention
arXiv:2610.15715v1 Announce Type: new Abstract: Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support ongoing computation and…
- arXiv cs.AIresearchVisible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops
arXiv:2610.15738v1 Announce Type: new Abstract: LLM optimization loops often show the proposer the candidates it has already tried and rejected, but leave it to the proposer to avoid them. We ask whether avoidance measur…
- arXiv cs.AIagentsGoogle Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation
arXiv:2610.15750v1 Announce Type: new Abstract: Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial Reasoning agent (GRA…
- arXiv cs.AIagentsAgent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
arXiv:2610.15788v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent, dominant speakers an…
- arXiv cs.AIresearchPassing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation
arXiv:2610.15797v2 Announce Type: replace Abstract: Planning and revision are intended to bring generated code closer to the task specification. Yet a mistaken interpretation can persist across the plan, implementation,…
- arXiv cs.AIresearchAttention Sinks in VLMs Are Borrowed, Not Seen
arXiv:2610.15855v2 Announce Type: replace Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a large share of attent…
- arXiv cs.AIresearchEngram Injection: A Study of Temporal Validity in Parametric Language-Model Memory
arXiv:2610.15882v2 Announce Type: replace Abstract: A stored fact may stop being valid when a user changes a preference or an event replaces an earlier one. We study whether a language model can learn these changes in it…
- arXiv cs.AIagentsRetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use
arXiv:2610.15884v3 Announce Type: replace Abstract: False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contract. RetryBench separates this error from realized…
- arXiv cs.AIresearchComparative Study of Canvas- and Coordinate-Based Geometry-Conditioned Neural Networks for Real-Time Prediction of Indoor Environments with Varying Room Dimensions
arXiv:2610.15885v1 Announce Type: new Abstract: Computational fluid dynamics (CFD) is computationally expensive for iterative building design. Deep learning surrogates offer faster predictions, but generalization across…
- arXiv cs.AIresearchLURE: a Phase-Labelled Synthetic Corpus of Online-Grooming Exchanges
arXiv:2610.15908v1 Announce Type: new Abstract: Phase-annotated conversational data is essential for studying the progression of online grooming of minors and for developing early warning tools. However, the only publicl…
- arXiv cs.AIresearchMulti-Horizon Explainable Queue Forecasting and Resource-Aware Decision Support for Intelligent Border Control Using LightGBM
arXiv:2610.15930v1 Announce Type: new Abstract: Border crossing points are stochastic service systems in which traffic demand, traveler categories, registration status, inspection requirements, staffing, and lane availab…
- arXiv cs.AIresearchThe Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much
arXiv:2610.15938v1 Announce Type: new Abstract: Evaluation of text generated by large language models (LLMs) is increasingly delegated to LLMs acting as judges, yet what such a judge must be shown remains unresolved. We…
- arXiv cs.AIagentsVision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment
arXiv:2610.15948v1 Announce Type: new Abstract: Proactive Smart Assistants (PSAs) increasingly use general knowledge, learned patterns from group-level data, patterns from individual user's data, and recent sensor observ…
- arXiv cs.AIresearchADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation
arXiv:2610.15956v1 Announce Type: new Abstract: Vision-language-action models for embodied navigation typically rely on RGB observations, limiting their applicability in lights-out industrial environments where visible i…
- arXiv cs.AIagentsSmall but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents
arXiv:2610.15964v1 Announce Type: new Abstract: A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass. Verifying a rewrite by…
- arXiv cs.AIagentsPopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination
arXiv:2610.15969v1 Announce Type: new Abstract: In multi-agent reinforcement learning, exposing a cooperator to partners with diverse strategies during training is key to better collaboration at test time. However, exist…
- arXiv cs.AIagentsRevocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways
arXiv:2610.15991v1 Announce Type: new Abstract: Distributed agent workflows cache delegated authority at tool gateways. Revocation may be reported at issuer commit, transport acknowledgment, or receiver persistence, alth…
- arXiv cs.AIresearchHandoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing
arXiv:2610.15993v1 Announce Type: new Abstract: We study how initial model selection, later handoff, and training targets affect success and cost in LLM tasks that span multiple turns. We compare several router architect…
- arXiv cs.AIresearchLarge language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework
arXiv:2610.15994v1 Announce Type: new Abstract: Representing individual-level behavioral heterogeneity is challenging in epidemiological modeling, particularly when empirical behavioral data are sparse. We assess the pot…
- arXiv cs.AIagentsComputational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance
arXiv:2610.16015v1 Announce Type: new Abstract: The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems. Agents built on large language models act through tools on…
- arXiv cs.AIresearchCross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings
arXiv:2610.16050v1 Announce Type: new Abstract: Personality assessment from asynchronous video interviews (AVIs) plays a crucial role in recruitment by enabling standardized and behaviorally grounded evaluation for job a…
- arXiv cs.AIagentsUnderstanding and Reducing Misalignment in Persuasion Optimization
arXiv:2610.16070v1 Announce Type: new Abstract: Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations. These tasks necessitate training models to be persuasive.…
- arXiv cs.AIresearchBeyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV
arXiv:2610.16074v1 Announce Type: new Abstract: Co-circulating influenza, COVID-19, and respiratory syncytial virus (RSV) create a shared hospital-admission burden, because beds, staff, testing capacity, and respiratory…
- arXiv cs.AIagentsHeterogeneous Agentic Coevolution
arXiv:2610.16078v1 Announce Type: new Abstract: Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rel…
- arXiv cs.AIresearchThe Sharp Directions Are Against You: Curvature Analysis of Activation Steering
arXiv:2610.16084v1 Announce Type: new Abstract: Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. T…
- arXiv cs.AIresearchGUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines
arXiv:2610.16108v1 Announce Type: new Abstract: Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consensus formation limit…
- arXiv cs.AIresearchConstructed regional photovoltaic generation fields improve ultra-short-term distributed solar forecasting
arXiv:2610.16110v1 Announce Type: new Abstract: Ultra-short-term forecasting of densely distributed photovoltaic (PV) systems remains challenging because external meteorological and satellite products may not adequately…
- arXiv cs.AIagentsBeyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues
arXiv:2610.16117v2 Announce Type: replace Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise. Yet e…
- arXiv cs.AIagentsImitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents
arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation (PI) as an architec…
- arXiv cs.AIresearchLarge Language Model Assisted Transportation Planning through a Differentiable User Equilibrium Layer
arXiv:2610.16140v1 Announce Type: new Abstract: Transportation planning has traditionally required substantial expertise in network modeling, traffic assignment, and optimization. As a result, strategic analyses such as…
- arXiv cs.AIagentsPhantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another
arXiv:2610.16141v1 Announce Type: new Abstract: LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its associatio…
- arXiv cs.AIagentsPollard: Governed Semantic Execution Trees for Framework-Independent AI Agent Control and Replay
arXiv:2610.16145v1 Announce Type: new Abstract: Agent frameworks can persist checkpoints, trace tool calls, and limit resource use, but these facilities often assign different identities to execution, governance, and rep…
- arXiv cs.AIagentsUncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints
arXiv:2610.16155v1 Announce Type: new Abstract: Interactive-agent evaluations commonly rely on standardized LLM-based user simulators that exhibit broadly cooperative behavior, potentially overlooking failures that arise…
- arXiv cs.AIresearchInteractive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction
arXiv:2610.16167v1 Announce Type: new Abstract: We propose the task of Interactive 4D Volumetric Liquid Forecasting: predicting the spatiotemporal evolution of a future dense 3D liquid velocity field conditioned on how a…
- arXiv cs.AIresearchProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
arXiv:2610.16175v1 Announce Type: new Abstract: Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety,…
- arXiv cs.AIresearchLabel-Centric Knowledge Retrieval for Zero-Shot Text Classification
arXiv:2610.16182v1 Announce Type: new Abstract: Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit their use for large-sc…
- arXiv cs.AIresearchCorrect Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces
arXiv:2610.16191v1 Announce Type: new Abstract: A model may select the correct answer yet fail to construct it through a sequence of local decisions. We introduce Choice2Seq, a diagnostic benchmark that measures correctn…
- arXiv cs.AIresearchOneShot: Label-Efficient Detector Weighting for Time Series Anomaly Detection
arXiv:2610.16219v1 Announce Type: new Abstract: Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore e…
- arXiv cs.AIagentsLearning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks
arXiv:2610.16231v1 Announce Type: new Abstract: As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing diverse group dynamic…
- arXiv cs.AIresearchScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context
arXiv:2610.16260v1 Announce Type: new Abstract: Current ASR models perform well on general benchmarks but still struggle with acoustically ambiguous words. Visual context can aid recognition in screen-based scenarios, ye…
- arXiv cs.AIresearchHardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution
arXiv:2610.16261v1 Announce Type: new Abstract: Mamba-based super-resolution models are efficient alternatives to Transformer-based restoration backbones, but their low-bit post-training quantization remains challenging…
- arXiv cs.AIagentsagent-risk: Risk Assessment for Changes to AI Agents
arXiv:2610.16280v1 Announce Type: new Abstract: Before changing a deployed AI agent (a stricter safety gate, a new model), organizations must approve the change, starting from existing logs. Extending classical risk anal…
- arXiv cs.AIagentsREVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces
arXiv:2610.16288v2 Announce Type: replace Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. Distillation and…
- arXiv cs.AIresearchMemory-Efficient Integer-Only Training of Deep Neural Networks
arXiv:2610.16298v1 Announce Type: new Abstract: Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision benchmarks retain floa…
- arXiv cs.AIresearchFON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention
arXiv:2610.16301v1 Announce Type: new Abstract: Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position signals bound to the…