AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrom Human Narrative to Harmonic Structure: A Human-Centered Investigation of Algorithmic Music Generation through the Chord Wheel Diagram
arXiv:2609.34735v1 Announce Type: new Abstract: Contemporary AI-based music generation can produce compositions that satisfy formal requirements of tonality and musical coherence. However, whether musical expression can…
- arXiv cs.AIresearchSeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing
arXiv:2609.34736v1 Announce Type: new Abstract: Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly from query embeddings,…
- arXiv cs.AIresearchPrivacy-Preserving Full-Body Meshing from mmWave Radar via Mesh Foundation Model Supervision
arXiv:2609.34768v3 Announce Type: replace Abstract: Millimeter-wave (mmWave) radar enables privacy-preserving human perception, but the extreme sparsity of point clouds from commercial single-chip sensors (mean ~6.5 poin…
- arXiv cs.AIresearchWhen Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety
arXiv:2609.34771v1 Announce Type: new Abstract: Reliable AI safeguards require both control mechanisms that reduce unsafe behavior and monitoring mechanisms that detect safety risks during model interactions. Established…
- arXiv cs.AIresearchBefore the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMs
arXiv:2609.34772v1 Announce Type: new Abstract: Multimodal diffusion language models generate responses by iteratively unmasking tokens, making each answer the endpoint of a multi-step trajectory rather than an immediate…
- arXiv cs.AIresearchPage-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs
arXiv:2609.34776v1 Announce Type: new Abstract: We study retrieval-augmented generation (RAG) for questions about French PDF documents when both the answer and its supporting document pages are evaluated. Five system var…
- arXiv cs.AIresearchApplying Language Models in Clinical Medicine: Recent Trends and Perspectives
arXiv:2609.34780v2 Announce Type: replace Abstract: The use and applicability of artificial intelligence (AI) in medical research and clinical practice has received increasing attention in the literature over recent year…
- arXiv cs.AIagentsBEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification
arXiv:2609.34785v1 Announce Type: new Abstract: Developing agents for hardware design and verification requires reliable correctness feedback. As a hardware specification may permit correct implementations with different…
- arXiv cs.AIresearchSTRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts
arXiv:2609.34799v2 Announce Type: replace Abstract: Language-conditioned trajectory generation is here, but its evaluation has not kept pace. Existing pedestrian trajectory metrics compare trajectories with real-world hu…
- arXiv cs.AIagentsSIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL
arXiv:2609.34805v1 Announce Type: new Abstract: Tree-structured reinforcement learning trains search agents by comparing alternative continuations and propagating terminal rewards to intermediate decisions. Adaptive expa…
- arXiv cs.AIagentsUniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning
arXiv:2609.34810v1 Announce Type: new Abstract: Reinforcement learning has become an effective approach to training language model agents, but sparse and delayed outcome rewards provide limited guidance for credit assign…
- arXiv cs.AIresearchSimulating Respondents, Not Single Questions: Coherent Survey Generation with Large Language Models
arXiv:2609.34828v1 Announce Type: new Abstract: Large language models are increasingly used to simulate response distributions in social surveys. Prior work has achieved accurate population-level simulation for individua…
- arXiv cs.AIresearchBV Loss: Block Verification-Aware Loss for Block Diffusion Speculative Decoding
arXiv:2609.34832v1 Announce Type: new Abstract: Diffusion drafters accelerate speculative decoding by proposing multiple tokens in parallel. Despite recent advances in speculative decoding through sequence-level drafting…
- arXiv cs.AIagentsNociception as a Control Primitive: Afferent Channels and Nociceptive Memory for Agents Deployed in One Body
arXiv:2609.34840v1 Announce Type: new Abstract: An agent deployed in a single body cannot learn how fast that body wears, because every trial that would reveal its wear resistance wears the body it would protect. We stud…
- arXiv cs.AIresearchCan We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
arXiv:2609.34848v1 Announce Type: new Abstract: RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for token-level credit. This exposes a fundamental coupling when updating step-level cre…
- arXiv cs.AIresearchFrom Soft Targets to Reward Signals: How Assignment and Reward Objectives Interact
arXiv:2609.34850v1 Announce Type: new Abstract: Soft preference targets specify supervision strength, and reward objectives convert that strength into learned reward signals. A central design question remains: how does a…
- arXiv cs.AIresearchAUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces
arXiv:2609.34854v1 Announce Type: new Abstract: Multimodal foundation models are increasingly used for evaluating and generating user interfaces (UIs), often producing seemingly reasonable aesthetic judgments and visuall…
- arXiv cs.AIresearchOn the Limits of Metacognitive Monitoring in LLMs
arXiv:2609.34864v1 Announce Type: new Abstract: Reliable decisions depend on recognizing when an answer may be wrong. In biological cognition, metacognitive monitoring can dissociate from task performance, raising the qu…
- arXiv cs.AIagentsOne Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair
arXiv:2609.34879v2 Announce Type: replace Abstract: Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Tool-agent repair seeks…
- arXiv cs.AIresearchFewer Assumptions by Design: A Reusable Skill for LLM-Assisted Verus Verification
arXiv:2609.34886v1 Announce Type: new Abstract: LLM-assisted Verus verification is a less tedious method to verify Rust implementations, but paired with self-referential structures, e.g., Doubly Linked Lists (DLLs)—not…
- arXiv cs.AIresearchDeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
arXiv:2609.34896v1 Announce Type: new Abstract: Safety alignment of large reasoning models (LRMs) via supervised fine-tuning (SFT) and reinforcement learning (RL) often yields near-perfect safety scores, yet this apparen…
- arXiv cs.AIresearchDual-Stream Simultaneous Translation via 2D Grid Attention
arXiv:2609.34902v1 Announce Type: new Abstract: Simultaneous machine translation must generate target tokens before the source input is complete. Existing approaches address this through post-hoc read-write policies, lea…
- arXiv cs.AIagentsDGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards
arXiv:2609.34913v1 Announce Type: new Abstract: Tool-using language-model agents can review enterprise projects as governance boards do: they read the evidence, apply written rules and decide whether the project may proc…
- arXiv cs.AIresearchRISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
arXiv:2609.34920v1 Announce Type: new Abstract: On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red…
- arXiv cs.AIagentsPDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents
arXiv:2609.34930v1 Announce Type: new Abstract: Large language model (LLM) agents are evolving from tool-calling systems that execute isolated instructions into task-oriented agents that pursue user goals through sustain…
- arXiv cs.AIagentsProactive Dialogue Policy Optimization via Cognitive-State Transition
arXiv:2609.34948v1 Announce Type: new Abstract: Proactive dialogue requires agents to continually adapt their policies to user feedback while progressing toward task objectives over multiple turns. To move beyond imitati…
- arXiv cs.AIresearchVD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection
arXiv:2609.34949v1 Announce Type: new Abstract: Few-shot visual anomaly detection is fundamentally a visual comparison task, requiring fine-grained inspection of a query against normal references. Many recent methods bas…
- arXiv cs.AIresearchAX is the New AEO
arXiv:2609.34951v3 Announce Type: replace Abstract: In 2023, AI models answered from training data and hallucinated when it ran out, and businesses were told to seed that knowledge. Models' training knowledge has since g…
- arXiv cs.AIresearchProofLoom: Proof-Obligation-Driven Theory Construction for Autoformalizing Research-Level Stochastic Optimization
arXiv:2609.34960v1 Announce Type: new Abstract: Formalizing research-level stochastic optimization in Lean requires both an algorithm model and domain theory connecting foundational libraries to convergence proofs. Revis…
- arXiv cs.AIresearchSafe Greenhouse Climate Control Using Lagrangian-Constrained PPO with Kolmogorov-Arnold Networks
arXiv:2609.34966v1 Announce Type: new Abstract: Greenhouse climate control balances economic return with maintaining temperature, humidity and CO2 within crop-adapted growth ranges. Conventional reinforcement learning (R…
- arXiv cs.AIagentsAction-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias
arXiv:2609.34971v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong performance on tool-use agentic tasks when given a fixed tool schema. Yet a tool schema is not the action space of an age…
- arXiv cs.AIagentsAPEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction
arXiv:2609.34973v1 Announce Type: new Abstract: Full-duplex voice agents can now listen, speak, use tools, and act during spoken interactions, but fluent dialogue does not guarantee correct completion of delegated profes…
- arXiv cs.AIagentsBefore Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive Interfaces
arXiv:2609.34974v1 Announce Type: new Abstract: LLM-based Web agents can autonomously complete user tasks, yet deceptive interfaces can steer them toward outcomes that conflict with users' interests. Existing defenses pr…
- arXiv cs.AIresearchFrom One-Shot Generation to Incremental Music Composition: Adapting a General-Purpose Instruction LLM for Persistent Symbolic Editing
arXiv:2609.34994v1 Announce Type: new Abstract: Most music-generation systems are still framed and evaluated primarily as producers of complete outputs, whereas composition often proceeds through successive revisions to…
- arXiv cs.AIresearchAutomated Feature Engineering, AutoML, and Decision-Focused Learning for Improved Energy Consumption Forecasting
arXiv:2609.35013v2 Announce Type: replace Abstract: The rising cost and demand for energy, together with environmental sustainability goals, create major challenges for energy management. Energy Consumption Forecasting (…
- arXiv cs.AIresearchTermJudge: A Document-Level Metric Judging, Not Counting, Terminology in Machine Translation Evaluation
arXiv:2609.35017v1 Announce Type: new Abstract: Existing automatic metrics for evaluating terminological use in machine translation (MT) penalise any divergence from a fixed reference, conflating translation errors with…
- arXiv cs.AIagentsEnvironmental requirements for the use of social information by artificial life agents using evolved plastic artificial neural networks
arXiv:2609.35018v1 Announce Type: new Abstract: Evolved Plastic Artificial Neural Networks (EPANNs) consist of two principal processes, the first, evolution, and the second, development and in-life learning. In the conte…
- arXiv cs.AIagentsAutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?
arXiv:2609.35025v1 Announce Type: new Abstract: Recent gains in language model capability have come more from data than from architecture. Frontier labs and data companies produce verifiable agentic tasks, which supervis…
- arXiv cs.AIagentsWebPageBench: Event-Level Verification and Controlled UI-Variant Generation for Web Agents
arXiv:2609.35026v1 Announce Type: new Abstract: We present WebPageBench, an open framework for evaluating web agents in which every task is verified from the interface's own event log. Six instrumented mock sites with br…
- arXiv cs.AIagentsJRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments
arXiv:2609.35032v2 Announce Type: replace Abstract: In complex embodied visual reasoning scenarios, an agent often has only a limited field of view, and the evidence needed to answer a question may be distributed across…
- arXiv cs.AIresearchPersona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation
arXiv:2609.35036v1 Announce Type: new Abstract: Persona prompting is widely used to construct user simulations with large language models (LLMs), yet it relies on a largely untested assumption: specifying one user attrib…
- arXiv cs.AIresearchWhat Drives Citations in Production Large Language Models? An Observational Multi-Method Study of Two Million AI Citations Across Ten Thousand Web Pages
arXiv:2609.35077v1 Announce Type: new Abstract: Production large language models retrieve and cite web pages alongside generated answers, yet the page-level features that predict citation frequency remain poorly characte…
- arXiv cs.AIagentsWhen Valid Tool Calls Change Meaning: Formation-Consistent Dispatch for LLM Agents
arXiv:2609.35088v1 Announce Type: new Abstract: Tool-enabled agents form calls from model-visible interfaces, while hosts later select their implementation. Standard dispatch omits the descriptor-handler relation. An unc…
- arXiv cs.AIresearchCan Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research
arXiv:2609.35089v2 Announce Type: replace Abstract: Meta-analysis is the synthesis of information from multiple sources to arrive at an overarching conclusion. There is a large need for meta-analysis in agricultural rese…
- arXiv cs.AIresearchDoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
arXiv:2609.35107v2 Announce Type: replace Abstract: We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evide…
- arXiv cs.AIresearchUsing Context Is Not Enough: Test-Time Training for Personalized Reward Modeling
arXiv:2609.35109v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) with human preferences, yet most pipelines learn a single reward model that overlooks…
- arXiv cs.AIresearchSol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge
arXiv:2609.35110v1 Announce Type: new Abstract: Video diffusion models are rapidly scaling and exhibiting enhanced generation capabilities. Among these recent advancements, MiniMax-H3 stands out as a highly capable, prod…
- arXiv cs.AIresearchDuplexCadence: Exact State and Execution from a Speech Model's Declared Timelines
arXiv:2609.35115v1 Announce Type: new Abstract: Full-duplex speech models support streaming interaction that listens and speaks at the same time. Serving them is governed by a strict, repeating deadline: conversation adv…
- arXiv cs.AIresearchTool Mediation Alters Refusal Mechanisms in Large Language Models
arXiv:2609.35117v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed with access to external tools, yet harmful tool-mediated interactions are less likely to be refused when compared to…
- arXiv cs.AIagentsFrom Migration to Calibration: Aligning Agents with Deployment Requirements
arXiv:2609.35149v3 Announce Type: replace Abstract: Deploying, migrating, or scaling an agent changes its model, support system, application, and users. Calibration should align the agent with destination requirements wi…