AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsInformation Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn Search Agents
arXiv:2607.06223v2 Announce Type: replace Abstract: Reinforcement learning (RL) improves large language model (LLM) agents on long-horizon search tasks that require multiple intermediate decisions before a final outcome.…
- arXiv cs.AIagentsCan Agentic Trading Systems Pay for Their Own Intelligence?
arXiv:2607.10286v3 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to pr…
- arXiv cs.AIagentsRegNetAgents: A Multi-Agent Framework for Cross-Network Regulatory Driver Identification in Cancer Genomics
arXiv:2607.14097v3 Announce Type: replace Abstract: We introduce RegNetAgents, an AI-oriented multi-agent framework for structured, query-driven regulatory candidate identification across heterogeneous gene regulatory ne…
- arXiv cs.AIresearchWhen to Plan: Learning to Select Between Reactive Control and Deliberative Planning
arXiv:2607.16421v2 Announce Type: replace Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the…
- arXiv cs.AIagentsSKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
arXiv:2608.02287v2 Announce Type: replace Abstract: Agent skills have become an important mechanism for equipping language-model agents with reusable procedural knowledge. However, providing skills alone does not guarant…
- arXiv cs.AIresearchFaster-WAM: Do World Action Models Need Deep Action Modules?
arXiv:2608.02365v2 Announce Type: replace Abstract: World Action Models (WAMs) build on pretrained video models, whose representations are grounded in physical dynamics and provide a natural basis for action prediction.…
- arXiv cs.AIagentsPractice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
arXiv:2608.12851v2 Announce Type: replace Abstract: LLM agents increasingly save experience from past tasks as reusable skills through skill evolution. When an agent completes an unsafe task, skill evolution can keep the…
- arXiv cs.AIagentsChronocooked: A Benchmark for Interval Timing in Reinforcement Learning Agents
arXiv:2608.16666v2 Announce Type: replace Abstract: Interval timing is extensively studied as an important aspect of human behaviour. As artificial agents are increasingly designed to function alongside humans, their int…
- arXiv cs.AIresearchQuantifying geographic domain shift to decouple the geospatial transferability of human mobility flow generation models
arXiv:2608.21567v3 Announce Type: replace Abstract: Human mobility serves as an essential proxy for understanding social, economic, and environmental dynamics in urban systems. Geospatial transferability, which measures…
- arXiv cs.AIagentsEDGE: Engine for Deterministic Graph Evaluation through Conversation Simulation from Graph Structured DSL Configuration
arXiv:2608.29971v2 Announce Type: replace Abstract: As agentic systems evolve into complex multi agent orchestration workflows, there is a growing and critical need for systematic frameworks that measures an agent's beha…
- arXiv cs.AIresearchThe Answer Is Not the Argument
arXiv:2609.00264v2 Announce Type: replace Abstract: Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors with a trusted reference answer. We ask whether answer access improves…
- arXiv cs.AIagentsHalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews
arXiv:2609.03580v2 Announce Type: replace Abstract: The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claim…
- arXiv cs.AIresearchSpeech Emotion Recognition Using CNN and Its Use Case in Digital Healthcare
arXiv:2406.10741v2 Announce Type: replace-cross Abstract: The process of identifying human emotion and affective states from speech is known as speech emotion recognition (SER). This is based on the observation that tone…
- arXiv cs.AIresearchLearning in the Recurrent State: Gradient Descent with Linear Recurrent Networks
arXiv:2410.11687v4 Announce Type: replace-cross Abstract: In-context learning lets a sequence model adapt to a new task from examples in its input. A prominent line of work shows how self-attention can be constructed to…
- arXiv cs.AIagentsGenerative AI for Autonomous Driving: Frontiers and Opportunities
arXiv:2505.08854v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for…
- arXiv cs.AIresearchRoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction
arXiv:2505.12224v5 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations into control…
- arXiv cs.AIresearchAPE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation
arXiv:2505.19912v3 Announce Type: replace-cross Abstract: We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modificat…
- arXiv cs.AIresearchGeometry-Centered 3D Latent World Models for Growing Surfaces
arXiv:2506.03173v3 Announce Type: replace-cross Abstract: Many physical systems do not merely move or deform; they grow, adding material and changing the geometry that a world model must represent. Existing world models…
- arXiv cs.AIresearch"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
arXiv:2506.09354v5 Announce Type: replace-cross Abstract: Mental health is a growing global concern, prompting interest in AI-driven solutions to expand access to psychosocial support. Peer support, grounded in lived exp…
- arXiv cs.AIresearchScaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval
arXiv:2509.00141v2 Announce Type: replace-cross Abstract: Statutory corpora and judicial decisions are growing faster than legal professionals can read them, while individual judgments often exceed the context limits of…
- arXiv cs.AIresearchSEER: Self-Enhancing Chain-of-Thought Compression for Reasoning Models
arXiv:2509.14093v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with high inference cost due…
- arXiv cs.AIresearchRoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking Modes
arXiv:2510.00154v2 Announce Type: replace-cross Abstract: Despite rapid progress in robotics, complex or long-horizon tasks remain a fundamental challenge. Most current approaches follow an open-loop paradigm with limite…
- arXiv cs.AIresearchOrder-Optimal Sample Complexity of Rectified Flows
arXiv:2601.20250v2 Announce Type: replace-cross Abstract: Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain…
- arXiv cs.AIresearchContinuous-Utility Direct Preference Optimization
arXiv:2602.00931v3 Announce Type: replace-cross Abstract: Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fin…
- arXiv cs.AIresearchMultiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)
arXiv:2602.03317v2 Announce Type: replace-cross Abstract: Quantitative imaging methods, such as magnetic resonance fingerprinting (MRF), aim to extract interpretable pathology biomarkers by estimating biophysical tissue…
- arXiv cs.AIresearchDoc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction
arXiv:2602.04892v2 Announce Type: replace-cross Abstract: Ensuring that API implementations and usage comply with natural language programming rules is critical for software correctness, security, and reliability. Formal…
- arXiv cs.AIresearchAttention-Mass Condensation for Sparse Decoding
arXiv:2602.06317v3 Announce Type: replace-cross Abstract: Attention-mass concentration creates an opportunity for sparse decoding, but retained mass alone does not guarantee a stable greedy decision: retrieval error, omi…
- arXiv cs.AIresearchBONSAI: Bayesian Optimization with Natural Simplicity and Interpretability
arXiv:2602.07144v3 Announce Type: replace-cross Abstract: Bayesian optimization (BO) is a popular technique for sample-efficient optimization of black-box functions. In many applications, the parameters being tuned come…
- arXiv cs.AIresearchMulti-encoder ConvNeXt Network with Smooth Attentional Feature Fusion for Multispectral Semantic Segmentation
arXiv:2602.10137v2 Announce Type: replace-cross Abstract: This work proposes MeCSAFNet, a multi-branch encoder-decoder architecture for land cover segmentation in multispectral imagery. The model separately processes vis…
- arXiv cs.AIresearchNovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning
arXiv:2602.20119v2 Announce Type: replace-cross Abstract: Solving complex long-horizon robotic tasks requires joint reasoning over abstract task structure and low-level physical interaction. While combining Vision-Langua…
- arXiv cs.AIresearchA Parameter-efficient Convolutional Approach for Camouflaged Weed Detection in Multispectral Aerial Imagery
arXiv:2603.06655v2 Announce Type: replace-cross Abstract: We introduce FCBNet, an efficient model designed for camouflaged weed detection. The architecture is based on a fully frozen ConvNeXt backbone, the proposed Featu…
- arXiv cs.AIresearchBi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection
arXiv:2603.13357v2 Announce Type: replace-cross Abstract: Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage embedding…
- arXiv cs.AIresearchAttention at Rest Stays at Rest: Breaking Visual Inertia to Mitigate Relation Hallucinations
arXiv:2604.01989v4 Announce Type: replace-cross Abstract: While multimodal large language models demonstrate strong entity-level perception, faithfully grounding relational interactions between objects remains a persiste…
- arXiv cs.AIresearchStoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics
arXiv:2604.03315v2 Announce Type: replace-cross Abstract: Storyboarding is a core skill in visual storytelling for film, animation, and games. However, automating this process requires a system to achieve two properties…
- arXiv cs.AIagentsA Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs
arXiv:2604.04614v3 Announce Type: replace-cross Abstract: Deep learning-based modeling of multimodal Electronic Health Records (EHRs) has become an important approach for clinical diagnosis and risk prediction. However,…
- arXiv cs.AIresearchA Survey of Secure Retrieval-Augmented Generation
arXiv:2604.08304v5 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) with external knowledge, but this access path creates security risks distinct from inhe…
- arXiv cs.AIresearchPerturbation Sensitivity of Maximum-Likelihood Pairwise Ranking in Computational Decision Systems
arXiv:2604.17805v5 Announce Type: replace-cross Abstract: Maximum-likelihood pairwise ranking is a com- mon computational mechanism for prioritization, reputation estimation, and comparison-driven decision support. Despi…
- arXiv cs.AIresearchSeeing Is No Longer Believing: Frontier Image Generation Models, Synthetic Visual Evidence, and Real-World Risk
arXiv:2604.24197v3 Announce Type: replace-cross Abstract: Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places. When these artifacts are presented…
- arXiv cs.AIresearchLinking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
arXiv:2605.00556v2 Announce Type: replace-cross Abstract: Partial driving automation creates a tension: drivers remain legally responsible while being less active in control. Meaningful human control (MHC), a normative f…
- arXiv cs.AIresearchFrom Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals
arXiv:2605.01616v3 Announce Type: replace-cross Abstract: Human behavior is difficult to observe continuously at scale, yet it leaves measurable traces in everyday device use. We test whether encrypted smartphone network…
- arXiv cs.AIresearchRamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
arXiv:2605.02003v4 Announce Type: replace-cross Abstract: Machine learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used technique…
- arXiv cs.AIresearchThe Metagame of Interpretability and Meta-Attributions
arXiv:2605.06295v2 Announce Type: replace-cross Abstract: How can an arbitrary attribution method be generalized from first principles to capture interactions? We answer this with the metagame, a conceptual framework for…
- arXiv cs.AIresearchTAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning
arXiv:2605.07943v2 Announce Type: replace-cross Abstract: Active vision -- where a policy controls its own gaze during manipulation -- has emerged as a key capability for imitation learning, with multiple independent sys…
- arXiv cs.AIresearchAPCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
arXiv:2605.09492v3 Announce Type: replace-cross Abstract: Reliable text generation is critical for deploying large language models (LLMs) in real-world applications, particularly in high-stakes domains such as medicine.…
- arXiv cs.AIresearchRestricting the Model, Missing the System: Measurement and Accountability in Offensive AI Governance
arXiv:2605.09504v3 Announce Type: replace-cross Abstract: We show that the instruments used to measure AI offensive capability fail in two ways: (i) they overstate harm, and (ii) they credit the model with capability tha…
- arXiv cs.AIresearchSteering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
arXiv:2605.10971v2 Announce Type: replace-cross Abstract: Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Cont…
- arXiv cs.AIresearchA Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training
arXiv:2605.14605v4 Announce Type: replace-cross Abstract: Model providers increasingly release the weights of large language models. Although these models are safety-aligned before release, their safeguards can often be…
- arXiv cs.AIresearchConstrained latent state modeling: A unifying perspective on representation learning under competing constraints
arXiv:2605.15995v3 Announce Type: replace-cross Abstract: Learning latent representations from temporal, multimodal, and partially observed data requires specifying what information a latent state should retain, discard,…
- arXiv cs.AIresearchBrain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
arXiv:2605.19352v2 Announce Type: replace-cross Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection…
- arXiv cs.AIagentsA Relative-Computability Theory of Self-Improving Agents
arXiv:2605.27381v4 Announce Type: replace-cross Abstract: Self-improving agents can acquire a procedure without knowing when its supporting teacher can safely be removed. We extend an oracle-relative model of evolving ag…