AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsTelling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
arXiv:2610.12445v4 Announce Type: replace-cross Abstract: Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via…
- arXiv cs.AIresearchBi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
arXiv:2610.12449v1 Announce Type: cross Abstract: Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetr…
- arXiv cs.AIagentsFrom Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. Open…
- arXiv cs.AIresearchMachine learning and information theory concepts towards an AI Mathematician
arXiv:2403.04571v2 Announce Type: replace Abstract: The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning. W…
- arXiv cs.AIagentsThought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Bootstrapped Prolog-based Chain-of-Thought
arXiv:2407.14562v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supporting various aspec…
- arXiv cs.AIagentsAgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System
arXiv:2507.14897v3 Announce Type: replace Abstract: Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However, agentic RL remains b…
- arXiv cs.AIagentsNeural Architecture Discovery via Autonomous Evolution
arXiv:2507.18074v2 Announce Type: replace Abstract: Recent progress in LLM agents has advanced the prospect of autonomous research. Yet whether AI can complete difficult long-horizon tasks, especially those that advance…
- arXiv cs.AIagentsMAPF-World: Action World Model for Multi-Agent Path Finding
arXiv:2508.12087v3 Announce Type: replace Abstract: Multi-agent path finding (MAPF) studies the problem of planning conflict-free paths for multiple agents from given start locations to designated goals, with application…
- arXiv cs.AIagentsMore Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
arXiv:2510.04532v2 Announce Type: replace Abstract: Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning…
- arXiv cs.AIagentsProof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
arXiv:2510.10931v3 Announce Type: replace Abstract: While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacki…
- arXiv cs.AIagentsMobileWorldBench: Towards Semantic World Modeling For Mobile Agents
arXiv:2512.14014v2 Announce Type: replace Abstract: World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approach…
- arXiv cs.AIresearchMissMAC-Bench: Building Solid Benchmark for Missing Modality Issue in Robust Multimodal Affective Computing
arXiv:2602.00811v2 Announce Type: replace Abstract: Current Multimodal Affective Computing (MAC) systems heavily rely on the completeness of multiple modalities to accurately understand human's affective state. However,…
- arXiv cs.AIagentsAgentic Critical Training
arXiv:2603.08706v2 Announce Type: replace Abstract: Imitation learning (IL) teaches language-model agents to reproduce expert actions but not to distinguish them from plausible mistakes. Self-reflection methods expose mo…
- arXiv cs.AIresearchEfficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
arXiv:2603.18166v2 Announce Type: replace Abstract: Crowd trajectory prediction plays a crucial role in public safety and management, where it can help prevent disasters such as stampedes. Recent works address the proble…
- arXiv cs.AIagentsBeyond Preset Identities: Selective Stance Accommodation and Interaction Reorganisation in Generative Agent Societies
arXiv:2603.23406v4 Announce Type: replace Abstract: Generative agent societies simulate people with assigned roles, preferences and relationships. As agents exchange arguments and choose partners, they can revise their p…
- arXiv cs.AIresearchSoft Tournament Equilibrium: Differentiable Set-Valued Inference for Non-Transitive Pairwise Comparisons
arXiv:2604.04328v4 Announce Type: replace Abstract: Soft Tournament Equilibrium (STE) is a differentiable layer for Top-Cycle (TC) and Uncovered-Set (UC) inference from reciprocal pair probabilities. Normalized log-sum-e…
- arXiv cs.AIresearchCan Large Language Models Reinvent Foundational Algorithms?
arXiv:2604.05716v2 Announce Type: replace Abstract: LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In t…
- arXiv cs.AIresearchBeyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
arXiv:2605.06213v3 Announce Type: replace Abstract: Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask cap…
- arXiv cs.AIagentsLiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning
arXiv:2605.07505v2 Announce Type: replace Abstract: We present LiteGUI, a new framework for building lightweight GUI agents. GUI interaction poses unique challenges due to the long-horizon nature of complex tasks and the…
- arXiv cs.AIagentsMedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
arXiv:2605.11814v2 Announce Type: replace Abstract: The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking.…
- arXiv cs.AIagentsEgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
arXiv:2605.27820v2 Announce Type: replace Abstract: As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and…
- arXiv cs.AIresearchVLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
arXiv:2607.04517v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions. In practice, however, their be…
- arXiv cs.AIagentsSAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing
arXiv:2607.13594v2 Announce Type: replace Abstract: LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that la…
- arXiv cs.AIagentsMasked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
arXiv:2607.16204v2 Announce Type: replace Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward di…
- arXiv cs.AIagentsCompute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV
arXiv:2607.23693v2 Announce Type: replace Abstract: Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest. Eviction and episodic-memory sche…
- arXiv cs.AIresearchGLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
arXiv:2607.28397v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approa…
- arXiv cs.AIagentsBeyond Component Testing: Validating Agentic AI Systems
arXiv:2607.29405v2 Announce Type: replace Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches validation practice…
- arXiv cs.AIresearchSolver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
arXiv:2608.03461v2 Announce Type: replace Abstract: Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermedia…
- arXiv cs.AIagentsCRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving
arXiv:2608.09202v2 Announce Type: replace Abstract: Modern autonomous vehicles are equipped with multiple sensors, such as cameras, LiDAR, and radar, for comprehensive environmental perception. However, robust cross-moda…
- arXiv cs.AIresearchConversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
arXiv:2608.10434v3 Announce Type: replace Abstract: Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-…
- arXiv cs.AIagentsDoes Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf
arXiv:2608.22697v5 Announce Type: replace Abstract: When shopping is delegated to AI agents, it is unclear whether the ranking advantage documented for humans persists. Across 7,000 sessions with five large language mode…
- arXiv cs.AIresearchMulti2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
arXiv:2608.26535v2 Announce Type: replace Abstract: Recent audio-video generators increasingly support joint conditioning on text, images, audio, and video. These capabilities also enable attacks that exploit cross-modal…
- arXiv cs.AIagentsA Score Is Not a Policy: Measuring the Value of Adaptive Revision
arXiv:2609.00874v2 Announce Type: replace Abstract: As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller preserve the strate…
- arXiv cs.AIagentsPolicy Learning with a Language Bottleneck
arXiv:2405.04118v4 Announce Type: replace-cross Abstract: Modern AI systems such as self-driving cars and game-playing agents can achieve superhuman performance, but often lack human-like generalization, interpretability…
- arXiv cs.AIresearchMooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
arXiv:2407.00079v5 Announce Type: replace-cross Abstract: Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates…
- arXiv cs.AIagentsAttention when you need
arXiv:2501.07440v3 Announce Type: replace-cross Abstract: Paying attention improves performance, but attention is metabolically costly, so how should a resource-efficient agent allocate it? We study optimal allocation st…
- arXiv cs.AIagentsSimultaneous Computation with Multiple Prioritizations in Multi-Agent Motion Planning
arXiv:2501.10781v2 Announce Type: replace-cross Abstract: Multi-agent path finding (MAPF) in large networks is computationally challenging. An approach for MAPF is prioritized planning (PP), in which agents plan sequenti…
- arXiv cs.AIresearchBEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting
arXiv:2501.19065v3 Announce Type: replace-cross Abstract: Long-term time-series forecasting supports a wide range of applications, including weather prediction and electricity demand planning. Frequency-domain methods ad…
- arXiv cs.AIresearchTowards Reasonable Concept Bottleneck Models
arXiv:2506.05014v3 Announce Type: replace-cross Abstract: We propose a novel, flexible, and efficient framework for designing Concept Bottleneck Models (CBMs) that enables practitioners to explicitly encode and extend th…
- arXiv cs.AIresearchHeterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging
arXiv:2506.15971v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) effectively bridges the domain gap between a labeled source domain and an unlabeled target domain, but assumes that the two d…
- arXiv cs.AIresearchAn Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
arXiv:2508.08833v4 Announce Type: replace-cross Abstract: Frontier large language models (LLMs) now reach near-ceiling accuracy on standard mathematical-reasoning benchmarks and gold-medal-level performance at the Intern…
- arXiv cs.AIresearchInverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
arXiv:2508.12466v3 Announce Type: replace-cross Abstract: Connecting pretrained vision and language models usually involves projecting image features into the language model's input space. Inverse-LLaVA reverses this map…
- arXiv cs.AIresearchCAF\'E: Causal Black-Box Testing of Machine Unlearning
arXiv:2509.16525v2 Announce Type: replace-cross Abstract: Machine learning models are increasingly deployed as software components that must evolve as requirements change. When specific training records or features must…
- arXiv cs.AIresearchAyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
arXiv:2511.02374v2 Announce Type: replace-cross Abstract: Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cu…
- arXiv cs.AIresearchTowards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations
arXiv:2511.04000v2 Announce Type: replace-cross Abstract: Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an efficient, scalable method…
- arXiv cs.AIresearchA PDE Perspective on Generative Diffusion Models
arXiv:2511.05940v3 Announce Type: replace-cross Abstract: Score-based diffusion models have emerged as a powerful class of generative methods, with successful applications across diverse domains. Despite their empirical…
- arXiv cs.AIresearchOne Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
arXiv:2512.13892v3 Announce Type: replace-cross Abstract: Reliable estimation of feature contributions in machine learning models is essential for transparency, algorithmic fairness, and regulatory compliance. While perm…
- arXiv cs.AIresearchGPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
arXiv:2512.21476v2 Announce Type: replace-cross Abstract: Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints and with different ca…
- arXiv cs.AIresearchSRUG: A Fusion-Driven Generator Network for Medical Image Translation
arXiv:2601.04785v2 Announce Type: replace-cross Abstract: MRI sequence synthesis aims to recover missing image contrast while preserving patient-specific anatomy. The choice of generation mechanism affects both optimizat…
- arXiv cs.AIresearchExplanation Multiplicity in SHAP: Characterization and Assessment
arXiv:2601.12654v3 Announce Type: replace-cross Abstract: SHAP explanations are widely used in high-stakes settings to justify decisions, yet they can differ substantially across repeated runs, even when the model, the i…