AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDWM: Separating World Effects from Actions in Latent World Models
arXiv:2607.18715v2 Announce Type: replace Abstract: Latent world models underpin much of modern model-based control, yet current action-conditioned formulations supervise the next-latent transition with a single, undiffe…
- arXiv cs.AIresearchCodifying the Judge: Scalable Evaluation via Program Distillation
arXiv:2607.22561v2 Announce Type: replace Abstract: LLM-as-a-judge has become the standard for automated evaluation, but it suffers from high cost, inference latency, and opaque decisions---limitations that undermine its…
- arXiv cs.AIresearchHow LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
arXiv:2607.22676v2 Announce Type: replace Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a model's pre-existing…
- arXiv cs.AIagentsSeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents
arXiv:2607.23263v2 Announce Type: replace Abstract: Deciding whether a trajectory actually fulfills its instruction determines how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we…
- arXiv cs.AIagentsClinLens: Towards Long-Horizon LLM Agents for Longitudinal Multimodal Clinical Data Science
arXiv:2607.26155v2 Announce Type: replace Abstract: Automating clinical data science requires agents to translate patient-centric objectives into executable workflows grounded in longitudinal multimodal evidence. Existin…
- arXiv cs.AIagentsNeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability
arXiv:2607.28942v3 Announce Type: replace Abstract: Recently Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and…
- arXiv cs.AIagentsAgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
arXiv:2608.00155v2 Announce Type: replace Abstract: Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independ…
- arXiv cs.AIagentsAssuming You Knew: Fixing an Epistemic Semantics for Flow Policies Using Agentic AI
arXiv:2608.00882v2 Announce Type: replace Abstract: Many high-level security requirements are about the allowed flow of information in programs and are difficult to make precise because they involve selective downgrading…
- arXiv cs.AIresearchMissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models
arXiv:2608.03740v2 Announce Type: replace Abstract: Recent GUI visual grounding models generate screen coordinates as digit-token sequences that are parsed into numerical values and mapped to executable clicks. This gene…
- arXiv cs.AIresearchStochasticity Is Not the Hard Part: Reduction and Complexity in Instructional Sequencing over Prerequisite DAGs
arXiv:2608.05455v2 Announce Type: replace Abstract: When a student must learn concepts connected by prerequisite dependencies, when does the order of instruction matter, and what does it cost to find the best one? We stu…
- arXiv cs.AIresearchFrom Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models
arXiv:2608.06578v2 Announce Type: replace Abstract: Frontier language models are trained with distinct data, objectives, and safety pipelines, but whether those differences produce measurably different behavior under ste…
- arXiv cs.AIresearchSDDBMs: Soft Denoising Diffusion Bridge Models
arXiv:2608.08594v3 Announce Type: replace Abstract: Diffusion bridge models leverage Doob's \(h\)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong potential in…
- arXiv cs.AIagentsModel Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
arXiv:2608.09696v5 Announce Type: replace Abstract: A primary goal of science is to learn mechanistic world models from limited experimental data, both to explain observations and to predict novel interventions. We intro…
- arXiv cs.AIagentsCausal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science
arXiv:2608.10030v3 Announce Type: replace Abstract: As AI agents are increasingly deployed in complex and new environments, knowing the conditions that influence their behavior becomes an indispensable step for their rel…
- arXiv cs.AIagentsSpatial Memory Agent: Experience-Grounded Procedural Memory for Spatial Intelligence
arXiv:2608.12743v3 Announce Type: replace Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability of VLMs, existi…
- arXiv cs.AIagentsAeroCopilotBench: Safety-Gated Evaluation of LLM Agents on Aircraft Emergency Procedures in an Executable Cockpit
arXiv:2608.16349v2 Announce Type: replace Abstract: Aviation knowledge question answering cannot directly assess the operational effectiveness and safety compliance of large language models throughout aircraft emergency…
- arXiv cs.AIagentsWhat is Missing from AI Post-Training AI: An Empirical Analysis
arXiv:2608.19072v2 Announce Type: replace Abstract: Large language model (LLM) agents can now post-train an LLM end-to-end, raising the prospect of recursive self-improvement (RSI). Yet this progress is measured by aggre…
- arXiv cs.AIagentsOptimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees
arXiv:2608.19993v2 Announce Type: replace Abstract: Loading reusable skill documents into a bounded context window has become a primary way large language model (LLM) agents acquire task-specific capabilities, which make…
- arXiv cs.AIagentsDon't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
arXiv:2608.21027v2 Announce Type: replace Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents operate over lon…
- arXiv cs.AIresearchEvaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance
arXiv:2608.21036v2 Announce Type: replace Abstract: The transport of dangerous goods by sea is a high-consequence activity governed by the International Maritime Dangerous Goods (IMDG) Code, a complex regulatory framewor…
- arXiv cs.AIagentsLitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platform
arXiv:2608.21374v2 Announce Type: replace Abstract: Literature reviews are essential to scientific progress, but rigorously evaluating automatically generated reviews remains difficult because many aspects of research ut…
- arXiv cs.AIresearchFrom Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning
arXiv:2608.21897v2 Announce Type: replace Abstract: Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDD…
- arXiv cs.AIagentsTraining Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning
arXiv:2608.21898v2 Announce Type: replace Abstract: Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding broken links, in…
- arXiv cs.AIagentsLocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents
arXiv:2608.25777v2 Announce Type: replace Abstract: Modern GUI-agent frameworks achieve strong desktop task performance with frontier API models, yet persistent control information often remains implicit in growing inter…
- arXiv cs.AIagentsA Systematic Survey of Agentic Skills: Architecture, Lifecycle, and Security
arXiv:2608.29596v2 Announce Type: replace Abstract: Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-hori…
- arXiv cs.AIresearchEscaping Reasoning Basin Collapse with History-Biased Search
arXiv:2609.00738v3 Announce Type: replace Abstract: Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternative reas…
- arXiv cs.AIagentsEvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
arXiv:2609.01526v2 Announce Type: replace Abstract: Scientific discovery depends on the ability to form hypotheses, test them through experiments, and revise them when evidence disagrees. Existing LLM agents support this…
- arXiv cs.AIagentsFresh Memory, Stale Plans: Derivation Currency for Distributed LLM-Agent Memory
arXiv:2609.03340v2 Announce Type: replace Abstract: A large language model (LLM) agent that inherits a plan through shared memory can hold the latest requirement yet act on a plan derived from an older one: fresh memory,…
- arXiv cs.AIagentsDuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents
arXiv:2609.03423v2 Announce Type: replace Abstract: Full-duplex voice agents must continuously decide when to speak, listen, backchannel, interrupt, overlap, and yield the conversational floor. Existing benchmarks evalua…
- arXiv cs.AIagentsSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding
arXiv:2609.05141v2 Announce Type: replace Abstract: Scientific papers require models to integrate evidence across text, equations, figures, tables, code, and datasets while preserving its provenance. Beyond answer correc…
- arXiv cs.AIresearchWhat Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
arXiv:2609.05198v2 Announce Type: replace Abstract: On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric…
- arXiv cs.AIagentsAgents' Overreliance on Unreliable Tools
arXiv:2609.05587v2 Announce Type: replace Abstract: LLM agents use tools to access information and perform computations beyond their parametric knowledge. Existing tool-use benchmarks evaluate whether agents select and c…
- arXiv cs.AIresearchRedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
arXiv:2609.07008v2 Announce Type: replace Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the phys…
- arXiv cs.AIagentsCausalVerify: End-to-End Verification of Causal Analyses by Language Models
arXiv:2609.07944v2 Announce Type: replace Abstract: Language models increasingly perform empirical analyses end to end, yet existing evaluations assess the written explanation or whether generated code executes, not whet…
- arXiv cs.AIagentsA Theory of Reliable Self-Evolution for Agent Harnesses
arXiv:2609.08175v2 Announce Type: replace Abstract: In harness self-evolution, agents modify their own prompts, code, tools, and orchestration while keeping the underlying language model fixed. Recent work has shown that…
- arXiv cs.AIresearchStructural Process Supervision for Latent Chain-of-Thought Reasoning
arXiv:2609.09928v2 Announce Type: replace Abstract: Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space emb…
- arXiv cs.AIresearchA Dominant Supplier Slows Recursive Drift More Than It Steers It
arXiv:2609.11146v3 Announce Type: replace Abstract: More and more of the text future language models learn from is written by a few of today's models. If one supplier writes most of a shared corpus, does it pull the mode…
- arXiv cs.AIagentsDynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents
arXiv:2609.14637v3 Announce Type: replace Abstract: Large language model agents are increasingly deployed for long-horizon task execution, raising a central granularity question for trajectory evaluation: whole-trajector…
- arXiv cs.AIagentsEnabling Creative Exploration for Vibe Design Agents
arXiv:2609.15078v3 Announce Type: replace Abstract: Vibe design agents translate natural-language requests into interfaces, yet repeated generations often converge on similar visual directions. We present an inference ar…
- arXiv cs.AIagentsIssue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
arXiv:2609.15207v2 Announce Type: replace Abstract: Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With grow…
- arXiv cs.AIresearchReason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings
arXiv:2609.15296v2 Announce Type: replace Abstract: Universal multimodal embedding (UME) maps multimodal inputs into a shared embedding space for diverse retrieval tasks. Recent methods improve embeddings through Chain-o…
- arXiv cs.AIagentsAlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery
arXiv:2609.15820v2 Announce Type: replace Abstract: Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-…
- arXiv cs.AIresearchThe Pain Axis: LLMs Represent Self-Directed Harm and Act on It
arXiv:2609.16247v2 Announce Type: replace Abstract: LLMs sometimes behave in ways resembling human emotional responses, and recent work identified internal representations that may underlie these behaviors. We ask whethe…
- arXiv cs.AIagentsImproving Causal Effect Estimation of Weighted RegressionBased Estimator using Neural Networks
arXiv:2110.15075v2 Announce Type: replace-cross Abstract: Estimating causal effects from observational data informs us about which factors are important in an autonomous system, and enables us to take better decisions. T…
- arXiv cs.AIresearchTraining-Free Uncertainty Estimation for Embedding Models
arXiv:2306.00206v3 Announce Type: replace-cross Abstract: Embedding models, often obtained via self-supervised learning, extract general-purpose representations from data. Quantifying the reliability of these representat…
- arXiv cs.AIresearchTowards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
arXiv:2407.08983v2 Announce Type: replace-cross Abstract: Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it becomes. However, curren…
- arXiv cs.AIresearchDetection and Characterization of Coordinated Online Behavior: A Survey
arXiv:2408.01257v3 Announce Type: replace-cross Abstract: Coordination is a fundamental aspect of life. The advent of social media has made it integral also to online human interactions, such as those that characterize t…
- arXiv cs.AIresearchHelp Me Help You: The Aggregate Value of Source and Target Data in Transfer Learning
arXiv:2408.16189v4 Announce Type: replace-cross Abstract: Transfer learning, in regression or classification, concerns problems where one aims to use imperfect data from a source distribution P to improve prediction w.r.…
- arXiv cs.AIresearchGoal-Conditioned Supervised Learning for Multi-Objective Recommendation
arXiv:2412.08911v4 Announce Type: replace-cross Abstract: Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model, aiming to achieve high and balanced performance across diver…
- arXiv cs.AIresearchEasier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots
arXiv:2412.16633v5 Announce Type: replace-cross Abstract: LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), and open_grippe…