AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsReward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents
arXiv:2610.22915v1 Announce Type: new Abstract: Open-ended tool agents can complete the same objective through different tool paths, and their quality depends jointly on the interaction trace, environment state, and fina…
- arXiv cs.AIresearchSep-Latent: Separator Tokens as Natural Compression Anchors for Implicit Reasoning
arXiv:2610.22924v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning through explicit Chain-of-Thought (CoT), but the associated computational overhead an…
- arXiv cs.AIresearchMultiple Turns, Short Horizons: Measuring Effective-Horizon Compression in Jailbreaks
arXiv:2610.22928v1 Announce Type: new Abstract: Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns. However, once an effective trajectory has been found, it is…
- arXiv cs.AIresearchDiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation
arXiv:2610.22973v1 Announce Type: new Abstract: Reinforcement learning improves diffusion models using rewards on generated images, but repeated denoising and gradient estimation make training expensive. We introduce \me…
- arXiv cs.AIagentsFrom Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents
arXiv:2610.22987v1 Announce Type: new Abstract: Coding agents use execution harnesses to constrain the consequences of prompt injection by enforcing permission boundaries. These systems deterministically intercept any ou…
- arXiv cs.AIresearchGOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
arXiv:2610.22992v1 Announce Type: new Abstract: Designing RNA sequences that fold into specific 3D structures is a fundamental challenge in therapeutics. Current RNA inverse folding methods typically condition on 3D back…
- arXiv cs.AIresearchEfficient CPU-GPU collaborative MoE inference via Adaptive Expert Assignment
arXiv:2610.23006v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making ex…
- arXiv cs.AIagentsAdaptation of Computer Use Agents to New Software with User Manuals
arXiv:2610.23012v1 Announce Type: new Abstract: Recent advances in multimodal foundation models have significantly improved the ability to operate real-world software through graphical user interfaces (GUIs) using visual…
- arXiv cs.AIresearchCausal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder Approach
arXiv:2610.23025v1 Announce Type: new Abstract: As AI-generated content becomes commoditized, economic value increasingly shifts from final artifacts to the upstream expertise used to specify inputs that steer LLM genera…
- arXiv cs.AIresearchASE: Attribution-Guided Semantic Evolution for Time Series Forecasting
arXiv:2610.23027v1 Announce Type: new Abstract: External text can supply predictive information absent from numerical histories, but its value depends on how it is represented, combined and deployed. We present Attributi…
- arXiv cs.AIagentsWhere Research Ideation Begins: Forward-Citation Supervision for Actionable Limitation Generation
arXiv:2610.23038v1 Announce Type: new Abstract: Automated research ideation has advanced rapidly, with multi-agent workflows that generate whole research ideas end to end. These frameworks leave largely unexamined the st…
- arXiv cs.AIresearchWhere Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation
arXiv:2610.23044v1 Announce Type: new Abstract: Rust is increasingly adopted as a memory-safe successor to C, and transpilers such as \crust{} can migrate entire C projects while preserving their behavior. Preserving beh…
- arXiv cs.AIagentsDistill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL
arXiv:2610.23048v1 Announce Type: new Abstract: Long-horizon interaction requires agents to make multiple decisions in a changing environment. Outcome-based GRPO lacks fine-grained guidance for intermediate decisions. Re…
- arXiv cs.AIagentsAgentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?
arXiv:2610.23051v1 Announce Type: new Abstract: The learning algorithm view of in-context learning (ICL) studies how fixed-parameter Transformers learn from supplied examples. Language model agents extend this setting th…
- arXiv cs.AIresearchRethinking GRPO for Large Reasoning Model Safety Alignment
arXiv:2610.23085v1 Announce Type: new Abstract: Large reasoning models (LRMs) exhibit strong reasoning capabilities but remain vulnerable to unsafe outputs. While Group Relative Policy Optimization (GRPO) is widely used…
- arXiv cs.AIagentsWebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning
arXiv:2610.23104v1 Announce Type: new Abstract: Real-world frontend development requires agents to compose reproduction, generation, modification, and repair over an evolving application state. Learning a general policy…
- arXiv cs.AIresearchLexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation
arXiv:2610.23141v1 Announce Type: new Abstract: Large Language Models (LLMs) have greatly assisted legal professionals. However, our empirical studies reveal that, when faced with underspecified consultations from non-ex…
- arXiv cs.AIresearchCIIR - Class-Indexed Interface Representation Learning
arXiv:2610.23151v1 Announce Type: new Abstract: Multimodal learning commonly assumes paired or synchronized observations, yet independently collected datasets rarely provide such correspondence. We introduce CIIR, a modu…
- arXiv cs.AIagentsQuAD: Quantitative Assessment via Distribution-Alignment for Qualitative Data Quality Enabled by a Content-Aware Multi-Agent System
arXiv:2610.23153v1 Announce Type: new Abstract: Assessing whether qualitative responses collected from semi-structured questions are ready for a particular analysis goal is a persistent challenge. Manual qualitative anal…
- arXiv cs.AIresearchAlgorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence
arXiv:2610.23161v2 Announce Type: replace Abstract: Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new pa…
- arXiv cs.AIresearchLongForge: Measuring and Improving Long-Context Instruction Data via Evidence-Assertion Reasoning Graphs
arXiv:2610.23167v1 Announce Type: new Abstract: Existing quality control for long-context instruction-tuning data is a one-shot judgment inside the generation pipeline that leaves only a scalar, revealing neither which d…
- arXiv cs.AIagentsOfficeTown: Generative Organizations for Evolving Agent Intelligence
arXiv:2610.23194v1 Announce Type: new Abstract: AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on materials, decisions, and feedback accumulated across assignmen…
- arXiv cs.AIresearchFuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing
arXiv:2610.23195v1 Announce Type: new Abstract: Collecting and labeling diverse test datasets for evaluating Deep Neural Networks (DNNs) is costly and time-consuming. This has motivated coverage-guided fuzzing techniques…
- arXiv cs.AIresearchNot All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning
arXiv:2610.23213v1 Announce Type: new Abstract: Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a singl…
- arXiv cs.AIresearchCharacterising and Analysing Retrieval-Augmented Generation Techniques
arXiv:2610.23226v1 Announce Type: new Abstract: The advent of Large Language Models (LLMs) across many application domains has increased the need for Retrieval-Augmented Generation (RAG) to reduce hallucinations and impr…
- arXiv cs.AIagentsBeyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response Generation
arXiv:2610.23256v1 Announce Type: new Abstract: Multimodal preference alignment often follows a score-based RLHF pipeline: a reward model is first trained to learn human preferences, then used to score on-policy response…
- arXiv cs.AIresearchReasoning Models Can Control Their Chains of Thought When They Tell Themselves To
arXiv:2610.23257v1 Announce Type: new Abstract: Chain-of-thought (CoT) controllability, the ability of reasoning models to control properties of their CoT, is consequential for both their usefulness and reliable oversigh…
- arXiv cs.AIagentsAnnotrace: A Workbench for Step-Level Annotation of Agent Traces
arXiv:2610.23284v3 Announce Type: replace Abstract: Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces b…
- arXiv cs.AIresearchCoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective
arXiv:2610.23290v1 Announce Type: new Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iterative denoising with bidirectional attention, which precludes the standard autoregressive key--value…
- arXiv cs.AIagentsOptimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research
arXiv:2610.23299v1 Announce Type: new Abstract: Most retrieval-augmented systems treat literature search as a single retrieval step followed by summarization. Real literature research works differently: the investigator'…
- arXiv cs.AIresearchSimOPD: Relational Knowledge Transfer for On-Policy Distillation
arXiv:2610.23306v1 Announce Type: new Abstract: A key challenge in on-policy distillation (OPD) is extracting effective supervision from teacher knowledge. Supervision from token probabilities may underutilize internal k…
- arXiv cs.AIresearchSelf-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
arXiv:2610.23311v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective Chain-of-Thou…
- arXiv cs.AIagentsFrom Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory
arXiv:2610.23313v1 Announce Type: new Abstract: Long-term agent memory requires recovering answer-relevant evidence dispersed across turns and sessions. Existing systems increasingly use structured memories and adaptive…
- arXiv cs.AIagentsAgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics
arXiv:2610.23317v1 Announce Type: new Abstract: Enterprise data analysis requires agents to connect analytical requests with knowledge distributed across databases, business documents, and existing example tasks. Without…
- arXiv cs.AIagentsRobust Function Calling for LLM Agents Under Interface Drift
arXiv:2610.23342v1 Announce Type: new Abstract: Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces ofte…
- arXiv cs.AIresearchOliO: ODE-based Linear Transition Operator for Self-Supervised Time Series Forecasting
arXiv:2610.23345v1 Announce Type: new Abstract: Self-supervised representation learning has advanced time series forecasting by capturing robust features from unlabeled data. However, existing contrastive and masking-bas…
- arXiv cs.AIresearchMonitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries
arXiv:2610.23362v1 Announce Type: new Abstract: Modern LLM applications rely on runtime monitors that inspect tool calls, traces, streams, detector outputs, and verifier inputs. This creates an interface-reliability prob…
- arXiv cs.AIresearchGenerative Policy Improvement from Observational Data
arXiv:2610.23436v1 Announce Type: new Abstract: We study how to improve decision policies from observational data to generate better actions when actions are complex, structured objects, such as text messages or images.…
- arXiv cs.AIresearchScoutRoute: Efficient Mixture-of-Experts Routing Using Internal Language Model Signals
arXiv:2610.23443v1 Announce Type: new Abstract: Efficient expert routing is a fundamental challenge in Mixture-of-Experts (MoE) systems, particularly for heterogeneous collections of independently trained Large Language…
- arXiv cs.AIagentsGatewayBench: Unified Capability and Security Evaluation Platform for MCP Gateways
arXiv:2610.23449v1 Announce Type: new Abstract: AI agents have increasingly interacted with external environments by invoking tools, with Model Context Protocol (MCP) emerging as a standard interface for connecting agent…
- arXiv cs.AIresearchS-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models
arXiv:2610.23465v1 Announce Type: new Abstract: Graph Large Language Models (GraphLLMs) enable powerful semantic understanding and reasoning over Text-Attributed Graphs (TAGs), while their semantic reasoning may exhibit…
- arXiv cs.AIresearchLocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMs
arXiv:2610.23511v1 Announce Type: new Abstract: Locally deployed large language models (LLMs) can reduce reliance on remote cloud services for natural language smart building automation, but backend-facing processing req…
- arXiv cs.AIresearchTrapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models
arXiv:2610.23525v1 Announce Type: new Abstract: Large language models (LLMs) are known to exhibit sycophancy by adjusting their responses toward users' expressed views. However, real users often justify their opinions th…
- arXiv cs.AIagentsSkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents
arXiv:2610.23554v1 Announce Type: new Abstract: Large language model agents increasingly rely on skills to extend their capabilities in complex tasks. However, scalable skill use requires Selective Skill Exposure (SSE):…
- arXiv cs.AIagentsDarwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents
arXiv:2610.23574v1 Announce Type: new Abstract: While Large Language Model (LLM) agents have demonstrated remarkable capabilities across complex tasks, they predominantly operate in isolated sessions, lacking the ability…
- arXiv cs.AIagentsRL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
arXiv:2610.23598v1 Announce Type: new Abstract: Time-aware retrieval is crucial for long-horizon LLM agents to effectively leverage ever-growing long-term memory. Existing methods focus on lexical or semantic similarity,…
- arXiv cs.AIagentsFrom Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents
arXiv:2610.23599v1 Announce Type: new Abstract: Large language model (LLM) agents tackle complex tasks through reasoning and interaction with external environments. Agent skills provide persistent, transferable capabilit…
- arXiv cs.AIresearchGEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs
arXiv:2610.23617v1 Announce Type: new Abstract: Identifying small-molecule structures from molecular formulas and tandem mass spectra remains a bottleneck in untargeted metabolomics and natural-product discovery. Even wh…
- arXiv cs.AIresearchOwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning
arXiv:2610.23670v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) monitoring offers actionable evidence for oversight AI systems, with the potential to enable early detection and intervention. However, existing…
- arXiv cs.AIresearchBeyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability
arXiv:2610.23722v2 Announce Type: replace Abstract: Understanding and simulating how subjective cognition and mental states emerge, evolve, and shape behavior is essential for advancing artificial intelligence toward dee…