AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhen PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders
arXiv:2610.27397v1 Announce Type: new Abstract: Learned post-training quantization (PTQ) calibration fits quantizer parameters on a small calibration set, and for a text embedder the natural supervision is retrieval rele…
- arXiv cs.AIresearchUnified Sharp Bounds on Probabilities of Causation
arXiv:2610.27398v1 Announce Type: new Abstract: Probabilities of causation (PoCs) have developed steadily, from the binary measures first introduced by Pearl to the non-binary setting recently studied by Shu et al. As th…
- arXiv cs.AIagentsProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions
arXiv:2610.27400v1 Announce Type: new Abstract: Large language model (LLM) agents are moving beyond reactive responses toward proactive assistance that anticipates user needs without explicit requests. However, existing…
- arXiv cs.AIagentsMore Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
arXiv:2610.27406v1 Announce Type: new Abstract: LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decis…
- arXiv cs.AIagentsKPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses
arXiv:2610.27417v1 Announce Type: new Abstract: A failed gaming trajectory reveals that an agent needs intervention, but not necessarily how its execution harness should change. Effective harness adaptation therefore req…
- arXiv cs.AIagentsHarness Self-Evolution for Long-Horizon Terminal Agents
arXiv:2610.27435v1 Announce Type: new Abstract: Long-horizon terminal agents may solve a task in one run yet fail across repeated runs. Stochastic errors can propagate through actions and context, creating a gap between…
- arXiv cs.AIresearchAsk to Distill: Learning to Synthesize Data for On-Policy Distillation
arXiv:2610.27450v1 Announce Type: new Abstract: On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can…
- arXiv cs.AIagentsRecoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement
arXiv:2610.27465v1 Announce Type: new Abstract: Agent platforms are starting to improve their own agents: they read a deployed agent's execution traces, derive a change, have an automated verifier approve it, and release…
- arXiv cs.AIagentsRuntime Control for AI Agents: Closing the Evaluation--Execution Gap in Operational Workflows
arXiv:2610.27480v1 Announce Type: new Abstract: Language-model agents increasingly participate in operational workflows where approvals, binds, and payments create commitments. An approval valid when issued may no longer…
- arXiv cs.AIagentsSecuring Agentic Commerce Through Behavior-Aware Fraud Detection and Cybersecurity for Trusted AI-Agent Payment Authorization
arXiv:2610.27483v1 Announce Type: new Abstract: The growing use of autonomous artificial intelligence agents in digital commerce creates new security concerns involving agent impersonation, unauthorized payments, comprom…
- arXiv cs.AIagentsThe More the Better? A Comparison of Single- and Multi-Agent LLM Setups on a Financial Review Task
arXiv:2610.27488v1 Announce Type: new Abstract: Practitioner guidance holds that a large language model reviews a document better when the work is divided among agents. We test a narrow form of it in a controlled compari…
- arXiv cs.AIresearchStructured-Token Attention for Fine-Grained mmWave Liquid Identification
arXiv:2610.27512v1 Announce Type: new Abstract: Fine-grained liquid identification requires a classifier to distinguish similar substances from compact millimeter-wave measurements. We investigate structured-token attent…
- arXiv cs.AIagentsWhen Health Assistants Agree Too Readily: A Benchmark of Time-Critical Self-Diagnosis
arXiv:2610.27518v1 Announce Type: new Abstract: Every day, more than 40 million people ask ChatGPT a health question, such as whether laptop posture explains a stiff neck and days of pounding headache. Posture is plausib…
- arXiv cs.AIagentsMemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories
arXiv:2610.27524v1 Announce Type: new Abstract: Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse earlier experience. However, such experience is diverse and evolving,…
- arXiv cs.AIagentsAutomated Multi-Agent Organization Design: From Architecture Search to Organizational Learning
arXiv:2610.27531v1 Announce Type: new Abstract: Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated search over agentic programs and interaction structures, with multi-…
- arXiv cs.AIagentsAct on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
arXiv:2610.27548v2 Announce Type: replace Abstract: When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existing agent evaluations largely measure task comple…
- arXiv cs.AIagentsRaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous Materials
arXiv:2610.27572v1 Announce Type: new Abstract: Porous-material adsorption studies require coordinated structure preparation, force-field selection, simulation, validation, and interpretation, making end-to-end automatio…
- arXiv cs.AIresearchWhen LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects
arXiv:2610.27573v1 Announce Type: new Abstract: Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues, yet the behavioral effects of manipulative outputs remain poorly q…
- arXiv cs.AIagentsThe Show-Up Attack: When Subagents Win Over Their Supervisor
arXiv:2610.27574v1 Announce Type: new Abstract: Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this also creates new attack surfaces: malicious agents may…
- arXiv cs.AIagentsDuplexLedger: Benchmarking Transactional Memory in Full-Duplex Speech Agents
arXiv:2610.27581v1 Announce Type: new Abstract: Full-duplex speech agents must update persistent memory while listening and speaking, yet it remains unclear which events should be stored, revised, or excluded. Existing b…
- arXiv cs.AIagentsBeyond Experience: Knowledge-Guided Evolution for NPU Kernel Generation
arXiv:2610.27588v1 Announce Type: new Abstract: LLM agents have become capable kernel engineers on mainstream GPU stacks, but they struggle on emerging accelerators such as Ascend NPUs, whose programming model is barely…
- arXiv cs.AIresearchMeta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
arXiv:2610.27598v1 Announce Type: new Abstract: As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hie…
- arXiv cs.AIresearchFrom Encoding to Generation: Towards Empathetic Large Language Models
arXiv:2610.27603v1 Announce Type: new Abstract: Empathetic interaction involves two distinguishable capacities: representing another person's emotional state (cognitive empathy) and generating an appropriate response to…
- arXiv cs.AIresearchTriGeoBench: A Multimodal Mathematical Geometry Benchmark with Figures and TikZ
arXiv:2610.27626v1 Announce Type: new Abstract: Multimodal Large Language Models show strong vision-language capabilities, yet their geometry-centric reasoning remains insufficiently understood. Existing mathematical ben…
- arXiv cs.AIresearchWhen Does Feedback Help? Auditing Learned Voltage-Clamp Experimental Design
arXiv:2610.27632v1 Announce Type: new Abstract: A learned scientific controller can outperform a misspecified planner without benefiting from feedback. We audit two synthetic voltage-clamp tasks with a training-selected…
- arXiv cs.AIresearchSCODEL: Shared Canonical Ontology Definitions for Food Entity Linking and Ontology-Grounded Recipe Knowledge Graphs
arXiv:2610.27637v1 Announce Type: new Abstract: Identifying recipe entities and linking them to ontology concepts is fundamental for semantic recipe understanding. However, food mentions in recipes are often ambiguous, c…
- arXiv cs.AIagentsCUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use Agents
arXiv:2610.27645v1 Announce Type: new Abstract: As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state and cause cascading fai…
- arXiv cs.AIagentsDoes Multi-Agent Collaboration Pay When Agents Serve Users? Testing Agent Scaling in Dual-Control Settings
arXiv:2610.27655v1 Announce Type: new Abstract: Multi-agent systems (MAS) built from language models are deployed on the premise that collaboration beats a single-agent system (SAS), yet when it pays is unclear. The most…
- arXiv cs.AIresearchWhen Can LLM Reasoning Reliably Reuse Intermediate Results?
arXiv:2610.27662v1 Announce Type: new Abstract: Sampling complete solutions gives large language models more chances to solve a problem, but each attempt starts again. For tasks with several subproblems, all required ans…
- arXiv cs.AIresearchInferring continuous cognitive traits from limited neuroimaging data using pairwise convolutional neural networks
arXiv:2610.27668v1 Announce Type: new Abstract: Individual differences in cognitive abilities vary widely, yet the structural brain features supporting these differences remain poorly understood. Traditional brain-behavi…
- arXiv cs.AIagentsReusing Multimodal Agents: Efficient Evaluation of Sound Designs in Games
arXiv:2610.27670v1 Announce Type: new Abstract: This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound design significantly in…
- arXiv cs.AIresearchTemporal Evidence Allocation For Longitudinal Clinical Retrieval: A Position And Technical Report
arXiv:2610.27682v1 Announce Type: new Abstract: Electronic health records are written to support care, not retrieval. Across years of oncology notes, the primary diagnosis is restated in report after report, while the ev…
- arXiv cs.AIresearchPattern Intelligence: Unsupervised, LLM-Interpreted Discovery of Systematic Underpayment and Denial Patterns in Healthcare Revenue Cycle Management
arXiv:2610.27684v1 Announce Type: new Abstract: Healthcare providers lose substantial revenue to systematic payer underpayments and claim denials, yet identifying the recurring, correctable patterns behind them remains l…
- arXiv cs.AIresearchEASformer: Environment-Action-State Alignment for Industrial Generative Ranking
arXiv:2610.27691v2 Announce Type: replace Abstract: Modern industrial ranking systems increasingly adopt generative recommendation (GR) paradigms, in which user behavior sequences and non-sequential (NS) features are tok…
- arXiv cs.AIresearchE8-QAT: Efficient 2-Bit Quantization-Aware Training with Implicit Lattice Codebooks
arXiv:2610.27699v1 Announce Type: new Abstract: Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar quantization encodes…
- arXiv cs.AIresearchHow Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection
arXiv:2610.27711v1 Announce Type: new Abstract: Under matched conditions, classifier-head fine-tuning (\textsc{cls}) paradigm consistently outperforms the LLM-as-Judge sequence-to-sequence (\textsc{s2s}) on binary halluc…
- arXiv cs.AIagentsWhen Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines
arXiv:2610.27714v1 Announce Type: new Abstract: When does experience memory help a closed-loop LLM driving agent? Published gains cannot say, because the two factors we find to matter most, which warmup experiences the p…
- arXiv cs.AIresearchHow Language Models Organize Task Information
arXiv:2610.27724v1 Announce Type: new Abstract: Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for prediction. We measure readou…
- arXiv cs.AIresearchRSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?
arXiv:2610.27735v2 Announce Type: replace Abstract: Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of this process has rec…
- arXiv cs.AIresearchGive the Model a Finger: Developmentally Aligned Evaluation of Counting in Vision-Language Models
arXiv:2610.27756v1 Announce Type: new Abstract: Vision-language models (VLMs) are exact on small sets and drift into estimation on larger ones, a profile reminiscent of children before they master counting. Children cros…
- arXiv cs.AIresearchCrystalAR: Autoregressive Modeling for Symmetric Crystal Generation
arXiv:2610.27762v2 Announce Type: replace Abstract: Deep generative modeling has achieved remarkable progress in crystal generation. Given the rich symmetries inherent in crystalline structures, recent work has sought to…
- arXiv cs.AIagentsRITE: Evaluating End-to-End Resilience to Silent Tool Errors in E-Commerce Agentic Systems
arXiv:2610.27777v1 Announce Type: new Abstract: Tool-using LLM agents increasingly answer e-commerce queries through multi-step tool interactions. The expected output of a tool call can shift between agent development an…
- arXiv cs.AIagentsGRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus
arXiv:2610.27781v1 Announce Type: new Abstract: Training LLM agents for policy-constrained tool environments, such as an airline backend with booking, refund, and cancellation policies, requires tasks that exercise the e…
- arXiv cs.AIagentsToward Agentic AI for the 6G Physical Layer: From Algorithm Discovery to Verified Baseband Silicon
arXiv:2610.27797v1 Announce Type: new Abstract: 6G will be designed faster than it can be built: AI-driven search already proposes physical-layer algorithms at machine speed, while carrying a single one onto embedded bas…
- arXiv cs.AIagentsLatBridge: Efficient and Stable Model Replacement in Latent-Communication Multi-Agent Systems
arXiv:2610.27813v1 Announce Type: new Abstract: Multi-agent systems rely on communication to complete tasks, and latent communication passes continuous representations to reduce text generation and re-encoding. However,…
- arXiv cs.AIresearchPrivacy-preserving inference on hosted models: a learned input-embedding transform for frozen Qwen3.8-27B
arXiv:2610.27817v1 Announce Type: new Abstract: Every prompt sent to a hosted language model is readable by whoever runs it. We study whether the prompt can remain on the client while the host receives transformed vector…
- arXiv cs.AIagentsCOMPASS: Routing via Capability-Oriented Model Profiling with Adaptive Search, Selection, and Tool Use
arXiv:2610.27822v1 Announce Type: new Abstract: LLM routing aims to select a capable model at low cost, but specialized routers can require updates as models and tasks change. We propose COMPASS, an agentic router in whi…
- arXiv cs.AIagentsSAPD: Learning from Agent Experience without Environment Interaction
arXiv:2610.27847v1 Announce Type: new Abstract: Scaling the training of Large Language Model (LLM) agents typically requires a large collection of executable environments, whose construction, maintenance, and operation c…
- arXiv cs.AIresearchPhysical Operating-Condition-Guided Vision-Language Matching for Cavitation Diagnosis in Industrial Pipeline Systems
arXiv:2610.27860v1 Announce Type: new Abstract: Cavitation diagnosis in industrial pipeline systems is challenging because acoustic responses vary substantially with operating conditions, while similar time-frequency pat…
- arXiv cs.AIresearchAutomatic Differentiation with Constraints in Forward and Inverse Problems
arXiv:2610.27888v2 Announce Type: replace Abstract: Approximate solutions of partial differential equations (PDEs) on unstructured grids can be represented on a graph. Numerical optimization involving stiff evolutionary…