AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests
arXiv:2610.14539v3 Announce Type: replace Abstract: Real-world business requests often leave key requirements unstated because frontline practitioners struggle to articulate rules they know from experience. Forward-deplo…
- arXiv cs.AIresearchAre Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
arXiv:2610.14542v2 Announce Type: replace Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has revealed that some…
- arXiv cs.AIresearchPsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation
arXiv:2610.14570v1 Announce Type: new Abstract: Large language models (LLMs) support social simulation, but faithfully reproducing real users requires grounding both structured platform decisions and language in sparse,…
- arXiv cs.AIresearchLearning after Execution with Action-Specific Credit
arXiv:2610.14573v1 Announce Type: new Abstract: Execution is often used as terminal feedback: it scores a generated program, but the resulting state is not used for another learning action. Learning after execution inste…
- arXiv cs.AIagentsCB-Agent: Concept-Based In-Context Learning for Sequential Action Selection
arXiv:2610.14574v1 Announce Type: new Abstract: In-context learning (ICL) allows large language models to use demonstrations without updating their parameters. For interactive agents, demonstrations are trajectories of r…
- arXiv cs.AIresearchIterate on an LLM, Serve on an SLM
arXiv:2610.14576v1 Announce Type: new Abstract: As frontier LLMs gain more capabilities, the cost to run them also goes up. At the same time, small language models (SLMs) also gain more capabilities but have largely been…
- arXiv cs.AIresearchDecoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning
arXiv:2610.14605v1 Announce Type: new Abstract: Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information. This surface-level criterion, however, masks two critic…
- arXiv cs.AIagentsFrom Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement
arXiv:2610.14625v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued development. Recent methods allow language agents to retain changes to…
- arXiv cs.AIagentsPEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents
arXiv:2610.14636v1 Announce Type: new Abstract: Terminal rewards make multi-turn agents trainable without step-level annotations, but group-relative advantages provide little guidance about which intermediate decisions t…
- arXiv cs.AIresearchAegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech
arXiv:2610.14643v1 Announce Type: new Abstract: Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical evidence. Protecting…
- arXiv cs.AIresearchShaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation
arXiv:2610.14644v1 Announce Type: new Abstract: Fine-grained mixture-of-experts (MoE) models commonly increase expert count by narrowing each expert, treating expert shape as a by-product of routing granularity. LatentMo…
- arXiv cs.AIagentsRASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution
arXiv:2610.14659v1 Announce Type: new Abstract: Streaming speech assistants can launch tools before users finish speaking, overlapping execution with incoming speech to reduce user waiting time. However, subsequent self-…
- arXiv cs.AIresearchA Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition
arXiv:2610.14680v1 Announce Type: new Abstract: Sign Language Recognition (SLR) presents complex challenges due to variable signing speeds and spatial intricacies. Specifically, Indian Sign Language (ISL) requires precis…
- arXiv cs.AIresearchAcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation
arXiv:2610.14693v1 Announce Type: new Abstract: Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large…
- arXiv cs.AIresearchJoint Discrete and SE(3) Diffusion for Protein Interface Design
arXiv:2610.14699v1 Announce Type: new Abstract: The design of high-affinity, target-specific protein binders is central to the development of modern therapeutics. However, existing protein-generation methods remain limit…
- arXiv cs.AIagentsDSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents
arXiv:2610.14700v1 Announce Type: new Abstract: Most text-to-SQL benchmarks provide the target database. In a large data catalog, however, choosing the sources is part of the problem: an agent must find every database ne…
- arXiv cs.AIresearchHow to Build a Benchmark That Actually Measures Taste
arXiv:2610.14707v2 Announce Type: replace Abstract: Expert-aligned "taste" benchmarks should reward craft judgment, not the ability to game the test. We introduce TasteBench, a pairwise good-vs-bad benchmark across visua…
- arXiv cs.AIresearchRelational Semantic Grounding for Test-Time Discovery
arXiv:2610.14721v1 Announce Type: new Abstract: Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones from a continuous unlabeled test stream after deployment. Existing TTD methods mainly rely o…
- arXiv cs.AIresearchMHWA: Multi-timescale Hierarchical World-Action Model
arXiv:2610.14727v1 Announce Type: new Abstract: Autoregressive world models have emerged as a powerful paradigm for sample efficient decision making, yet their open loop rollouts often exhibit increasing drift that leads…
- arXiv cs.AIagentsThink in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems
arXiv:2610.14736v1 Announce Type: new Abstract: Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate solutions through natural-language prompting. However, OPRO's optimiz…
- arXiv cs.AIresearchSAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability
arXiv:2610.14745v1 Announce Type: new Abstract: Extreme low-bit weight-only quantization is an effective approach to reducing the deployment costs of large language models. Below 3 bits, scalar quantization often suffers…
- arXiv cs.AIresearchEqual-information evaluation of credit assignment in modular financial reinforcement learning
arXiv:2610.14750v1 Announce Type: new Abstract: Credit assignment in modular financial reinforcement learning is difficult to evaluate because an attributed signal may improve a component loss without adding decision-rel…
- arXiv cs.AIresearchGateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
arXiv:2610.14754v1 Announce Type: new Abstract: Hybrid language models interleave Gated DeltaNet (GDN) layers, whose recurrent memory has a fixed size, with full-attention layers, whose key-value (KV) cache grows with th…
- arXiv cs.AIresearchCUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation
arXiv:2610.14763v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data. Effective unlearning must remove target infor…
- arXiv cs.AIagentsHow Should a Camera-First AI Agent Work?
arXiv:2610.14772v2 Announce Type: replace Abstract: Camera-first agents must act on the visual world as it unfolds. We argue that the central obstacle for future camera-first agents is not recognition ability - multimoda…
- arXiv cs.AIagentsProgAgent: Learning Tool Orchestration through Programmatic Training
arXiv:2610.14774v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where…
- arXiv cs.AIresearchLYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement
arXiv:2610.14777v1 Announce Type: new Abstract: LLM-powered data analytics aims to translate natural language instructions into executable analytical programs over underlying data. However, existing approaches, whether t…
- arXiv cs.AIagentsCounterfactual Regret for Reflective Agents with Lean-Verified Guarantees
arXiv:2610.14790v1 Announce Type: new Abstract: Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selection and action gene…
- arXiv cs.AIresearchGREAT-ESDD: Graph Edge Attention Network for Effectively Steered Delivery Decisions
arXiv:2610.14792v1 Announce Type: new Abstract: Online, same-day delivery requires operators to constantly update their routes, and the routing cost for deliveries increases with the number of customers. Out-of-home (OOH…
- arXiv cs.AIresearchCESNET-TimeSeries26: A Multi-Year Network Traffic Time Series Dataset for Annual Seasonality, Concept Drift, and Long-Term Anomaly Detection
arXiv:2610.14799v1 Announce Type: new Abstract: Forecast-based models are fundamental to network traffic management and anomaly detection. However, it is essential to evaluate these forecasting models over extended perio…
- arXiv cs.AIagentsASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox
arXiv:2610.14807v2 Announce Type: replace Abstract: Evaluating autonomous agents requires examining whether they can translate goals into coherent action across extended interactions. In persistent environments, this req…
- arXiv cs.AIagentsA Reference Architecture for Integrating Agentic AI into Enterprise Software: Responsibilities, Interactions, and Variability
arXiv:2610.14818v1 Announce Type: new Abstract: Agentic AI moves generative AI applications toward systems that coordinate reasoning, enterprise context, model inference, and external actions. Integrating these capabilit…
- arXiv cs.AIagentsEvoCowork: A Benchmark for Real-World Office Tasks
arXiv:2610.14828v1 Announce Type: new Abstract: Office workflows are a demanding testbed for self-improving agents because their deliverables must be correct, natively editable, and mutually consistent. A central questio…
- arXiv cs.AIresearchPre-Registered Genesis Accounting for Recursive Self-Improvement: First Audited Operator-Genesis Events in a Physics-Discovery Runtime
arXiv:2610.14843v1 Announce Type: new Abstract: Claims of recursive self-improvement are easy to make and hard to falsify: did improvement come from re-using designer-provided mechanisms, or from mechanisms the system au…
- arXiv cs.AIagentsPEAM: On-device Communication Agent for Personalized, Efficient and Autonomous Mobile Network Configuration
arXiv:2610.14855v1 Announce Type: new Abstract: The growing deployment of compact large language models on smartphones is enabling autonomous on-device decision-making, such as emerging mobile GUI agents. However, many m…
- arXiv cs.AIresearchWeatherBridge: Forecast-Aware Multi-Source Input Adaptation for Pretrained Weather Forecasting Models
arXiv:2610.14863v1 Announce Type: new Abstract: Data-driven weather forecasting models are commonly trained on ERA5, yet operational deployment must use timely initial states from physics-based numerical weather predicti…
- arXiv cs.AIagentsBeyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning
arXiv:2610.14877v1 Announce Type: new Abstract: Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing methods typically rely…
- arXiv cs.AIagentsMARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL
arXiv:2610.14883v1 Announce Type: new Abstract: We present MARL-BattleGrounds (MARL-BGs), an easy-to-use JAX-native benchmark for heterogeneous and competitive multi-agent reinforcement learning (MARL), designed to be sa…
- arXiv cs.AIresearchProbable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents
arXiv:2610.14912v1 Announce Type: new Abstract: Language models are increasingly used to create synthetic survey samples, also called silicon samples. Decision models are a new class of language models that return a prob…
- arXiv cs.AIresearchBridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
arXiv:2610.14913v1 Announce Type: new Abstract: Reinforcement learning (RL) is essential for adaptive decision-making, e.g., robust Meta-RL and domain randomization (DR), and efficient post-training of large language mod…
- arXiv cs.AIagentsWorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions
arXiv:2610.14915v1 Announce Type: new Abstract: Developing terminal-based agents for long-horizon execution demands synthetic tasks that tightly couple complex instructions with authentic, interactive environments. Howev…
- arXiv cs.AIagentsSkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications
arXiv:2610.14918v1 Announce Type: new Abstract: Evaluating an agent's ability to strictly satisfy diverse and procedurally complex requirements is essential to determining its practical reliability. Conducting such an ev…
- arXiv cs.AIresearchPredicting how model propensities generalize out of distribution
arXiv:2610.14937v1 Announce Type: new Abstract: How do language models generalize from their training data? This is a central challenge for alignment: models reliably learn their training distribution given enough sample…
- arXiv cs.AIresearchVC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning
arXiv:2610.14939v1 Announce Type: new Abstract: GRPO-style reinforcement learning has advanced vision-language reasoning, but its sequence-level rewards provide limited credit assignment for individual reasoning tokens.…
- arXiv cs.AIagentsMCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents
arXiv:2610.14956v1 Announce Type: new Abstract: The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a standardized interf…
- arXiv cs.AIagentsWhat Survives When Activation Steering Is Used as Memory
arXiv:2610.14958v2 Announce Type: replace Abstract: Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later. Facts and preference…
- arXiv cs.AIresearchAlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery
arXiv:2610.14959v3 Announce Type: replace Abstract: Formulaic alpha mining seeks to discover executable expressions that capture predictive market signals in a vast, noisy search space. Recent LLM-based approaches use pr…
- arXiv cs.AIagentsSkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
arXiv:2610.14966v1 Announce Type: new Abstract: Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand tas…
- arXiv cs.AIresearchFleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization
arXiv:2610.14970v1 Announce Type: new Abstract: With the rapid evolution of large language models (LLMs), there is an increasing demand for effective personalization techniques that can adapt model behavior to individual…
- arXiv cs.AIresearchSingle-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad
arXiv:2610.14980v1 Announce Type: new Abstract: We present a generator of Thai klon pad verse, one stanza from a short topic, and evaluate it against human verse on held-out topics. The generator is a masked language mod…