AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsMatched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents
arXiv:2610.34298v1 Announce Type: new Abstract: Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the dec…
- arXiv cs.AIagentsCTXAgent - Self-Controlled Context Management of LLM Agents
arXiv:2610.34425v1 Announce Type: new Abstract: Agent harnesses keep long sessions inside the context window by compacting the history when a token threshold is crossed. We study an alternative in which the model manages…
- arXiv cs.AIresearchFrom Outranking Flow Scores to Linear Programs: Group Decision Making in PROMETHEE II
arXiv:2610.34481v1 Announce Type: new Abstract: We study inverse and consensus analysis for PROMETHEE II ranking problems when the performance table is fixed. Existing approaches in PROMETHEE-based sensitivity and consen…
- arXiv cs.AIagentsWhat Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
arXiv:2610.34491v1 Announce Type: new Abstract: Generative models increasingly expose a reasoning effort setting that lets users scale inference-time compute, trading higher cost for potentially improved performance. Use…
- arXiv cs.AIagentsCaliMem: Search-Efficient Data Agent via Calibrated Memory
arXiv:2610.34500v1 Announce Type: new Abstract: Data curation is a first-order design choice in machine learning, yet tailoring training data to a downstream model and task remains costly in labor, expertise, and compute…
- arXiv cs.AIresearchHow Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3
arXiv:2610.34523v1 Announce Type: new Abstract: Learning through exploration and using newly acquired knowledge to achieve goals are central capabilities of general intelligence. Understanding these capabilities requires…
- arXiv cs.AIresearchHow Much Information Can We Fit inside a Transformer?
arXiv:2610.34553v1 Announce Type: new Abstract: How efficiently can transformers store factual knowledge? The answer to this question has implications for both model design and understanding the limits of transformer-bas…
- arXiv cs.AIagentsAgentic AI Orchestration Framework for Spatial Intelligence: Supply Chain Deployment
arXiv:2610.34569v1 Announce Type: new Abstract: Industrial spatial decisions are assembled across systems that share neither a reference frame nor an owner, and analysts spend substantial effort reconciling those systems…
- arXiv cs.AIagentsRethinking Verification in Agent Harnesses
arXiv:2610.34577v1 Announce Type: new Abstract: Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' wor…
- arXiv cs.AIresearchHobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget
arXiv:2610.34582v1 Announce Type: new Abstract: We describe HobbyLM, a family of small sparse Mixture-of-Experts (MoE) models trained from scratch with a few hundred to a few thousand dollars of rented GPU time. The core…
- arXiv cs.AIresearchA Battery for AI Propensity Measurement: Rubrics, Synthetic Item Banks, and Annotations
arXiv:2610.34614v1 Announce Type: new Abstract: We release a battery of 28 propensities for AI research, with expert-written rubrics, synthetic datasets, and annotated demand intervals, built with the method of Romero-Al…
- arXiv cs.AIresearchCSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception
arXiv:2610.34616v1 Announce Type: new Abstract: Indoor context deciphered by ambient sensing underpins many applications, from assisted living to smart buildings, yet remains weakly connected to the language-aligned para…
- arXiv cs.AIresearchOne Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition
arXiv:2610.34623v1 Announce Type: new Abstract: Text injection trains speech recognition models on unpaired text alongside paired audio. We feed the speech encoder synthetic input derived from text so the whole model lea…
- arXiv cs.AIagentsInferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants
arXiv:2610.34640v1 Announce Type: new Abstract: Large language model (LLM)-based personal agents are increasingly deployed to handle everyday tasks on users' behalf. These agents have access to private user information,…
- arXiv cs.AIagentsSlowLab: Benchmarking Autonomous AI Agents on a Year of Experiments They Cannot Undo
arXiv:2610.34644v1 Announce Type: new Abstract: AI agents are increasingly proposed as autonomous experimenters, yet the benchmarks that test them mostly offer cheap experiments that answer at once. Experiments in physic…
- arXiv cs.AIresearchAdaTutor: Adaptive Tutoring through Pedagogical Strategy Selection
arXiv:2610.34659v1 Announce Type: new Abstract: Effective tutoring requires determining not only what information to provide, but also which form of assistance to deliver. A tutor may address the same student error using…
- arXiv cs.AIagentsHierarchical Task Network planning in the Goal Lifecycle
arXiv:2610.34668v1 Announce Type: new Abstract: Goal reasoning (GR) is the process by which intelligent agents continually reason about the goals they are pursuing, which may lead to goal change, for instance when opport…
- arXiv cs.AIresearchCurriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience
arXiv:2610.34677v1 Announce Type: new Abstract: Hierarchical task knowledge enables efficient problem solving by allowing previously acquired skills to be reused across tasks and problem instances. In this paper, we inve…
- arXiv cs.AIresearchTopic-Level Fairness in Retrieval-Augmented Generation
arXiv:2610.34683v1 Announce Type: new Abstract: Group fairness in retrieval-augmented generation (RAG) systems is typically evaluated using metrics aggregated across queries. However, such metrics can conceal topic-level…
- arXiv cs.AIresearchMovable-Element Multi-Functional RIS-Assisted Hybrid RSMA-NOMA: A Constrained Hybrid Reinforcement Learning Approach
arXiv:2610.34701v1 Announce Type: new Abstract: In this work, we propose a movable-element (ME) multi-functional reconfigurable intelligent surface (MF-RIS) architecture, termed MM-RIS, which integrates element mobility…
- arXiv cs.AIresearchSafe by Benchmark, Unsafe in Practice: Lessons from 1331 Child-Related AI Incidents
arXiv:2610.34705v1 Announce Type: new Abstract: AI systems are increasingly present in children's everyday environments: education, entertainment, social networks, and toys. Their safety is typically assessed at the mode…
- arXiv cs.AIresearchIntervene, Calibrate, Discover: Learning Causal Structure from Pixels
arXiv:2610.34711v1 Announce Type: new Abstract: Learning high-level causal variables from low-level observations is a central problem for artificial intelligence. With known node semantics but an unknown graph, visual re…
- arXiv cs.AIagentsSearchHorizonBench: A Benchmark for Search Value in AI Agents
arXiv:2610.34714v1 Announce Type: new Abstract: AI agents must decide when another search is worth its cost. Answer-success probabilities capture question difficulty, while this decision requires estimating the additiona…
- arXiv cs.AIresearchPrefetch-Steered Routing: Deterministic Cache-Aware Expert Selection for Offloaded Mixture-of-Experts Decoding
arXiv:2610.34721v1 Announce Type: new Abstract: When a Mixture-of-Experts (MoE) model does not fit in GPU memory, batch-1 decoding is dominated by copying expert weights from host memory. Cache-aware routing reduces thes…
- arXiv cs.AIagentsCEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
arXiv:2610.34722v1 Announce Type: new Abstract: Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions withi…
- arXiv cs.AIagentsHarness-Model Collaboration for Long-Horizon Continual Learning
arXiv:2610.34724v1 Announce Type: new Abstract: Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persist…
- arXiv cs.AIagentsSKALOS: Learning to Distinguish Similar Skills with Capability Graphs
arXiv:2610.34728v1 Announce Type: new Abstract: Skills provide LLM agents with reusable procedural knowledge, making appropriate skill selection essential for reliable agent behavior. As skill libraries expand, distingui…
- arXiv cs.AIagentsQuery-Driven Learning for Lifted Reasoning
arXiv:2610.34747v1 Announce Type: new Abstract: Learning and reasoning are both essential to intelligent agents, but have traditionally been treated as two separate stages: first learning a knowledge base from data (or t…
- arXiv cs.AIagentsThe Right Fact, the Wrong Decision: SciValidityBench for Scientific Agent Memory
arXiv:2610.34767v1 Announce Type: new Abstract: Most agent-memory benchmarks frame long-term memory as retrieval: can an agent recover the relevant record from a long and evolving history? Scientific agents face a strict…
- arXiv cs.AIagentsScope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition
arXiv:2610.34777v1 Announce Type: new Abstract: This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pipelines. In the IJCAI 2026 OpenClaw Agent Security A…
- arXiv cs.AIresearchArya Forge: Auditing Validation and Release Approval for Financial Instruction Data
arXiv:2610.34778v1 Announce Type: new Abstract: Financial instruction-data pipelines must distinguish content validity from permission to release a particular dataset. Arya Forge combines typed records, current-content c…
- arXiv cs.AIresearchUncovering the Turing Test's Latent Signal: Indistinguishability as a Reward
arXiv:2610.34781v1 Announce Type: new Abstract: Can a model learn by trying to fool another model? We show that it can. Inspired by the Turing Test and its recent generalization to arbitrary distinguishers, we introduce…
- arXiv cs.AIagentsCentralized Critics for N-Agent Ad Hoc Teamwork
arXiv:2610.34799v1 Announce Type: new Abstract: Centralized training with decentralized execution (CTDE) has become the dominant paradigm in multi-agent reinforcement learning (MARL), motivating extensive study of what p…
- arXiv cs.AIresearchTrustJev: Separating Policy Authority from Untrusted Evidence in LLM-Based Decisions
arXiv:2610.34826v1 Announce Type: new Abstract: Decision models enable software to select from predefined actions using natural language inputs. However, the external evidence that supplies facts for these decisions may…
- arXiv cs.AIresearchLogic Hijacking of RAG: Single-Document Poisoning via Local Optimization
arXiv:2610.34829v2 Announce Type: replace Abstract: Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented Generation (RAG). However, existing attacks predominantly rely on e…
- arXiv cs.AIagentsCollective Emergent Alignment: Measuring and Amplifying Interaction-Induced Reasoning Alignment in Multi-Agent LLMs
arXiv:2610.34836v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems can exhibit emergent behaviors through interaction, yet whether a similar phenomenon exists for reasoning alignment remains l…
- arXiv cs.AIresearchBeyond Behaviour: A Stimulus-Response Safety Evaluation of Vision-Language-Action Models
arXiv:2610.34837v1 Announce Type: new Abstract: Humans exhibit biological sensitivity to safety-critical stimuli that can trigger defensive action. Across three models and two video benchmarks, we investigate whether sim…
- arXiv cs.AIresearchDecoyCount: Evaluating Visual-Reasoning Misalignment in Counting
arXiv:2610.34855v1 Announce Type: new Abstract: Visual counting benchmarks report whether vision-language models produce the correct number, but not whether errors arise from perception or reasoning. We introduce DecoyCo…
- arXiv cs.AIresearchUniGFM-RAG: Unify Graph Foundation Models and Large Language Models for End-to-End Retrieval and Reasoning
arXiv:2610.34866v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown remarkable capabilities across tasks, but they still struggle with complex reasoning that requires integrating scattered knowledge.…
- arXiv cs.AIresearchGADAR: Generalizing Across Domains via Action Ranking for Classical Planning
arXiv:2610.34868v1 Announce Type: new Abstract: Learned policies for classical planning act without search, but each is tied to the domain it was trained on: network modules per action schema, parameters per predicate, o…
- arXiv cs.AIresearchDocTalk: Enhancing Medical Knowledge Retrieval via Fine-tuned Large Language Models with Chain-of-Thought Reasoning for Robust Clinical Decision Support
arXiv:2610.34871v1 Announce Type: new Abstract: Objective: The rapid advancement of large language models (LLMs) in healthcare has opened new possibilities for AI-assisted clinical decision-making; however, safe and effe…
- arXiv cs.AIagentsClinVerse: A Realistic Multi-Agent Diagnostic Environment for Training and Evaluating Medical Agents
arXiv:2610.34878v1 Announce Type: new Abstract: Disease diagnosis is a key application of large language model (LLM) agents in healthcare. However, existing medical agents are primarily trained and evaluated with static…
- arXiv cs.AIresearchThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
arXiv:2610.34886v1 Announce Type: new Abstract: Reasoning language models generate thousands of tokens per answer, and generation speed is limited by memory bandwidth, so storing weights in two bits instead of bfloat16 c…
- arXiv cs.AIresearchPhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds
arXiv:2610.34921v1 Announce Type: new Abstract: Physical reasoning underpins how embodied systems understand and act in the physical world, yet vision-language models (VLMs) remain unreliable on questions about dynamics…
- arXiv cs.AIresearchStop or Clarify? Experience-Conditioned Active Fact Verification
arXiv:2610.34941v1 Announce Type: new Abstract: Fact-verification benchmarks score the final label, while an interactive verifier must first decide whether the available evidence is sufficient. We focus on that intermedi…
- arXiv cs.AIresearchDecision Model Factory: Building Specialized Sovereign Decision Models
arXiv:2610.34956v1 Announce Type: new Abstract: Decision needs vary with each application, language, and deployment environment. The Decision Model Factory turns those needs into specialized, sovereign models on demand.…
- arXiv cs.AIresearchC-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails
arXiv:2610.34961v1 Announce Type: new Abstract: Despite the remarkable capabilities of large language models (LLMs) across diverse applications, they remain vulnerable to generating content that violates safety regulatio…
- arXiv cs.AIresearchWhy Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
arXiv:2610.34994v1 Announce Type: new Abstract: Modern large language models (LLMs) often exhibit overconfident errors, assigning high confidence to incorrect predictions and thereby undermining reliability in real-world…
- arXiv cs.AIresearchCritic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery
arXiv:2610.35011v1 Announce Type: new Abstract: Deep narrative understanding requires distinguishing what happens from how it is presented, moving beyond the chronological fabula to decode the sjuzet, the discursive orga…
- arXiv cs.AIagentsMultiscale Policy Optimization for Long-Horizon LLM Agents
arXiv:2610.35013v1 Announce Type: new Abstract: Long-horizon LLM agents interact with their environments through complete assistant turns while generating each action token by token. We observe that critic values vary pr…