AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
arXiv:2609.28414v1 Announce Type: cross Abstract: Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most:…
- arXiv cs.AIagentsAgent-Editing World Model: Rethinking World Modeling for LLM Agents
arXiv:2609.28416v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existi…
- arXiv cs.AIresearchOrder-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning
arXiv:2609.28442v2 Announce Type: replace-cross Abstract: Reordering a set of mathematical rules without changing its meaning should preserve the correct answer, but must a model's internal representations stay invariant…
- arXiv cs.AIresearchCan LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark
arXiv:2609.28449v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in coding tasks, but their ability to reason about code execution remains unclear. Existing repository-level QA benchma…
- arXiv cs.AIresearchWhere Should I Join? Robot Group Joining via Language-Guided Goal Prediction
arXiv:2609.28467v1 Announce Type: cross Abstract: Social navigation typically assumes a specified goal and focuses on reaching it while respecting social conventions, whereas robot group joining requires predicting where…
- arXiv cs.AIresearchRetrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems
arXiv:2602.16715v2 Announce Type: replace Abstract: We explore the potential of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Graph-based RAG (GraphRAG) for generating Design Structure Matrices…
- arXiv cs.AIresearchContextual Information Allocation in Shared-State Cognitive Models: An Information-Theoretic Bound
arXiv:2602.16716v4 Announce Type: replace Abstract: Context-sensitive behavior can be modeled by enriching an internal state, by allowing a response rule to access context directly, or by preserving a shared state while…
- arXiv cs.AIresearchInterPol: De-anonymizing LM Arena via Interpolated Preference Learning
arXiv:2603.15220v3 Announce Type: replace Abstract: Strict anonymity of model responses is a key for the reliability of voting-based leaderboards, such as LM Arena. While prior studies have attempted to compromise this a…
- arXiv cs.AIresearchCalibration and transfer in indicator-based assessments of artificial consciousness
arXiv:2603.27597v2 Announce Type: replace Abstract: Research on artificial consciousness increasingly shifts evaluation from behaviour to internal architecture. Theory-based indicators are used to update probability assi…
- arXiv cs.AIagentsPreregistered Belief Revision Contracts
arXiv:2604.15558v2 Announce Type: replace Abstract: Deliberative multi-agent systems allow agents to exchange messages and revise beliefs over time. While this interaction is meant to improve performance, it can also cre…
- arXiv cs.AIresearchAnon: Extrapolating Adaptivity Beyond SGD and Adam
arXiv:2605.02317v3 Announce Type: replace Abstract: Adaptive optimizers such as Adam and non-adaptive methods like SGD exhibit distinct generalization capabilities across different architectures. Prior tunable optimizers…
- arXiv cs.AIresearchANO: Robust Policy Optimization via Bounded, Redescending Gain Fields
arXiv:2605.02320v3 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment, yet its hard-clipping mechanism and unconstrained alternatives (e.g., SPO) sit at…
- arXiv cs.AIagentsMobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
arXiv:2605.26114v3 Announce Type: replace Abstract: We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating propriet…
- arXiv cs.AIresearchTOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
arXiv:2606.27161v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, w…
- arXiv cs.AIresearchWarranted Attention: Learning What to Pass from Attention to Prediction
arXiv:2606.30139v4 Announce Type: replace Abstract: Relevance of information read by attention does not guarantee that its contribution benefits the current prediction. We propose Warrant, which learns how strongly atten…
- arXiv cs.AIresearchA rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks
arXiv:2607.02175v2 Announce Type: replace Abstract: Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinical performance i…
- arXiv cs.AIresearchWhen do prophets profit in prediction markets?
arXiv:2607.06166v3 Announce Type: replace Abstract: Prediction markets aggregate dispersed beliefs into prices that act as probabilistic forecasts of uncertain events. Classical theory establishes how a better-than-marke…
- arXiv cs.AIagentsOmni-Decision: Evidence-Ledger Planning for Omni-Modal Agents
arXiv:2607.11433v3 Announce Type: replace Abstract: Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy multimodal observatio…
- arXiv cs.AIresearchTACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring
arXiv:2608.03952v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-language (ESL) learners. Effective ESL tutoring, however,…
- arXiv cs.AIresearchMemory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
arXiv:2608.23982v2 Announce Type: replace Abstract: Scientific reasoning requires language models to retrieve specialized knowledge and incorporate it reliably into multi-step computation. Conditional memory provides an…
- arXiv cs.AIresearchHANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering
arXiv:2608.29088v2 Announce Type: replace Abstract: Multimodal question answering remains sensitive to noisy, incomplete, and weakly grounded evidence. Long unstructured contexts can introduce redundancy and encourage un…
- arXiv cs.AIagentsValerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration
arXiv:2609.09418v3 Announce Type: replace Abstract: World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although WAMs are rapidl…
- arXiv cs.AIagentsPRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
arXiv:2609.09664v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer,…
- arXiv cs.AIagentsSci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
arXiv:2609.11243v2 Announce Type: replace Abstract: Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These capabilities req…
- arXiv cs.AIresearchFrom Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development
arXiv:2609.11493v2 Announce Type: replace Abstract: Chemistry, Manufacturing and Controls (CMC) process development generates an enormous body of technical information across a multi-stage, knowledge-intensive continuum…
- arXiv cs.AIresearchA Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops
arXiv:2309.10164v3 Announce Type: replace-cross Abstract: We develop a decentralized Perception-Action-Communication (PAC) system for multi-robot teams that enables them to collaborate in large scale, outdoor environment…
- arXiv cs.AIresearchOptimizing watermarks for large language models
arXiv:2312.17295v2 Announce Type: replace-cross Abstract: With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An impor…
- arXiv cs.AIresearchRadiomics and artificial Intelligence for thyroid cancer diagnosis: Concepts, challenges, and solutions
arXiv:2404.07239v2 Announce Type: replace-cross Abstract: Thyroid cancer is an increasing global health concern that requires advanced diagnostic methods. The application of AI and radiomics to thyroid cancer diagnosis i…
- arXiv cs.AIresearchThe Mathematical Theory of Double Descent as Shrinkage, not Overfitting: Matching Bounds for Path-Regularized Multilayer Neural Networks
arXiv:2503.02129v4 Announce Type: replace-cross Abstract: We give a nonasymptotic generalization theory for multilayer fully connected neural networks trained with path regularization, for general Lipschitz losses and wi…
- arXiv cs.AIresearchSMDDFNet: State-space Modeling and Dynamic Dual Fusion Network for Traffic Sign Detection
arXiv:2505.05491v2 Announce Type: replace-cross Abstract: Traffic sign detection is a challenging visual signal processing task for advanced driver assistance, where small objects, scale variation, and occlusion limit co…
- arXiv cs.AIresearchAdaDim: Dimensionality Adaptation for SSL Representational Dynamics
arXiv:2505.12576v3 Announce Type: replace-cross Abstract: A key factor in effective Self-Supervised learning (SSL) is preventing dimensional collapse, where higher-dimensional representation spaces ($R$) span a lower-dim…
- arXiv cs.AIresearchDiscrete optimal transport is a strong audio adversarial attack
arXiv:2509.14959v4 Announce Type: replace-cross Abstract: In this paper, we investigate discrete optimal transport (DOT) as a black-box attack against modern automatic speaker verification (ASV) and anti-spoofing counter…
- arXiv cs.AIagentsWAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
arXiv:2510.01354v2 Announce Type: replace-cross Abstract: Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection…
- arXiv cs.AIagentsUniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization
arXiv:2510.03161v4 Announce Type: replace-cross Abstract: With the rapid advancements in image generation, synthetic images have become increasingly realistic, posing significant societal risks, such as misinformation an…
- arXiv cs.AIresearchOffline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data
arXiv:2511.04541v2 Announce Type: replace-cross Abstract: Slate recommender systems (RecSys) present users with ordered sets of interacting items (e.g., playlists). We investigate whether large language models (LLMs) can…
- arXiv cs.AIresearchParameter Importance-Driven Continual Learning for Foundation Models
arXiv:2511.15375v2 Announce Type: replace-cross Abstract: Domain-specific post-training often causes catastrophic forgetting, making foundation models lose their general reasoning ability and limiting their adaptability…
- arXiv cs.AIresearchFine-Tune, Then Rectify
arXiv:2511.19486v3 Announce Type: replace-cross Abstract: Driven by recent advances in artificial intelligence, a growing literature has demonstrated the potential of using large language models (LLMs) as scalable surrog…
- arXiv cs.AIresearchParameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Models
arXiv:2511.19636v3 Announce Type: replace-cross Abstract: In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on fundamentally different i…
- arXiv cs.AIresearchSelf-Improvement as Coherence Optimization: A Theoretical Account
arXiv:2601.13566v2 Announce Type: replace-cross Abstract: Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surpr…
- arXiv cs.AIresearchLORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights
arXiv:2602.17510v3 Announce Type: replace-cross Abstract: We introduce LoRA-CRAFT (\textbf{C}ross-layer \textbf{R}ank \textbf{A}daptation via \textbf{F}rozen \textbf{T}ucker), abbreviated CRAFT throughout, an extremely p…
- arXiv cs.AIresearchA Very Big Video Reasoning Suite
arXiv:2602.20159v4 Announce Type: replace-cross Abstract: Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in…
- arXiv cs.AIresearchMed-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution
arXiv:2603.05308v4 Announce Type: replace-cross Abstract: Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the po…
- arXiv cs.AIresearchUsing Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning
arXiv:2603.08930v2 Announce Type: replace-cross Abstract: This paper introduces a benchmark for evaluating whether vision-language models (VLMs) can generate plant simulation configurations from imagery using in-context…
- arXiv cs.AIresearchMessyKitchens: Contact-rich object-level 3D scene reconstruction
arXiv:2603.16868v2 Announce Type: replace-cross Abstract: Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achieve…
- arXiv cs.AIresearchLook Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
arXiv:2603.16932v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolu…
- arXiv cs.AIagentsWhen AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection
arXiv:2603.18740v5 Announce Type: replace-cross Abstract: Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, ranging from interactive…
- arXiv cs.AIresearchFSCE: A Target-Aware Frequency-Spatial Collaborative Enhancement Framework for Noise-Resilient SAR ATR
arXiv:2603.21565v3 Announce Type: replace-cross Abstract: Synthetic aperture radar automatic target recognition (SAR ATR) is severely challenged by coherent speckle noise, whose interference can be progressively amplifie…
- arXiv cs.AIresearchSoftmax gradient policy for variance minimization and risk-averse multi armed bandits
arXiv:2604.00241v2 Announce Type: replace-cross Abstract: Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and nu…
- arXiv cs.AIresearchLitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape
arXiv:2604.02600v3 Announce Type: replace-cross Abstract: Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively…
- arXiv cs.AIresearchTiAb Review Plugin: A Browser-Based Tool for AI-Assisted Study Selection in Systematic Reviews
arXiv:2604.08602v2 Announce Type: replace-cross Abstract: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills, and full-text screening has remained outside the sco…