AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchTAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
arXiv:2609.37349v1 Announce Type: cross Abstract: Multi-step visual retrieval-augmented generation (RAG) answers complex questions by repeatedly retrieving visual evidence, updating an intermediate state, and deciding wh…
- arXiv cs.AIresearchPort-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling
arXiv:2609.37351v1 Announce Type: cross Abstract: Test-time compute scaling has emerged as a cornerstone of advanced machine reasoning, yet performing iterative deliberation directly within continuous latent representati…
- arXiv cs.AIagentsEncore: Few-Shot Agentic Discovery of Manipulation Strategies
arXiv:2609.37359v1 Announce Type: cross Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in wh…
- arXiv cs.AIresearchCompiling Learning Problems into Adaptation Programs for Language Models
arXiv:2609.37371v1 Announce Type: cross Abstract: Model adaptation is typically governed by a fixed recipe, even though different update programs can produce substantially different behavioral outcomes. We introduce adap…
- arXiv cs.AIresearchDo-JEPA: From Masking to Intervention in Latent World Models
arXiv:2609.37378v1 Announce Type: cross Abstract: Latent world models are trained to predict what happens next, so nothing in their objective separates what an action caused from what merely co-occurred with it. Object-m…
- arXiv cs.AIresearchComplexity-Aware Evaluation of LLM Comprehension
arXiv:2609.37405v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for software engineering tasks that require understanding existing source code, including behavior prediction, function…
- arXiv cs.AIresearchSimultaneous Neural Optimal Transport
arXiv:2609.37424v1 Announce Type: cross Abstract: Optimal Transport (OT) provides a principled framework for learning transformations between probability distributions from unpaired samples. In many applications, however…
- arXiv cs.AIresearchLazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension
arXiv:2609.37426v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture. However, most methods…
- arXiv cs.AIresearchLearning to Retrieve Missing Evidence for Long-Term Memory QA
arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scattered across distant t…
- arXiv cs.AIresearchEngineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited Compute
arXiv:2609.37447v1 Announce Type: cross Abstract: How strong can an AlphaZero-style chess system become under limited training compute when its entire learning loop is engineered for efficiency? We train from random init…
- arXiv cs.AIagentsBackdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
arXiv:2609.37468v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an agent observes and it…
- arXiv cs.AIresearchRegime Boundary Alignment for Evidence-Gated Question Answering
arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence is missing. We trace…
- arXiv cs.AIresearchRisk-Controlled Selective LLM Answering by Pricing Label-Free Checks
arXiv:2609.37493v1 Announce Type: cross Abstract: Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error rate among served an…
- arXiv cs.AIagentsEvaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
arXiv:2609.37501v1 Announce Type: cross Abstract: We propose RegLLM, a diagnostic harness for bounded autonomy in regulated agentic workflows. It instruments six trustworthiness signals: citation validity, source groundi…
- arXiv cs.AIresearchHierarchical Compression of Vision-Language Model Benchmarks
arXiv:2609.37515v1 Announce Type: cross Abstract: Thorough evaluation of vision-language models (VLMs) has become prohibitively expensive, as benchmarks span an ever-broader spectrum of capabilities and new models arrive…
- arXiv cs.AIresearchVideo2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning
arXiv:2609.37519v1 Announce Type: cross Abstract: Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched demonstrations. A cen…
- arXiv cs.AIresearchDScale: Scaling Block-Diffusion Speculative Decoding with Adaptive Verification
arXiv:2609.37532v1 Announce Type: cross Abstract: Growing large language model applications demand efficient inference. At high concurrency, block-diffusion speculative decoding suffers from verification padding, rejecte…
- arXiv cs.AIresearchRisk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning
arXiv:2609.37554v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as high-level planners in robot navigation, but their outputs may become unreliable when instructions are ambiguous, un…
- arXiv cs.AIagentsConcealing LLM-Based Multi-Agent Topology via Phantom Structure Injection
arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collaborative reasoning over…
- arXiv cs.AIresearchTReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning
arXiv:2609.37581v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at visual understanding and reasoning but often incur substantial inference costs due to the large number of visual tokens. Recent vis…
- arXiv cs.AIresearchFedSocket: Recipient-Executable Knowledge Exchange for Heterogeneous Multimodal Federated Learning
arXiv:2609.37582v2 Announce Type: replace-cross Abstract: Federated knowledge must remain usable by recipients with different modalities, private architectures, and tasks. We present FedSocket, which makes recipient exec…
- arXiv cs.AIresearchLearning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection
arXiv:2609.37586v1 Announce Type: cross Abstract: Continual audio deepfake detection requires learning newly emerging deepfake methods while retaining discrimination of previously encountered speech. Existing dataset-inc…
- arXiv cs.AIresearchReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling
arXiv:2609.37587v1 Announce Type: cross Abstract: Longitudinal electronic health record (EHR) modeling requires integrating new visits with an expanding patient history. Yet the continual accumulation of clinical informa…
- arXiv cs.AIresearchCredit-Guided Policy Improvement for Test-time Adaptive Vision-Language Navigation
arXiv:2609.37591v1 Announce Type: cross Abstract: Test-time adaptation for vision-language navigation (TTA-VLN) enables pretrained policies to adapt online to unseen environments using only test-time observations and int…
- arXiv cs.AIresearchIndependent Verification Paths Are Not Independent: A Case Study of Common-Mode Failure in a Satellite Catalogue Pipeline
arXiv:2609.37603v1 Announce Type: cross Abstract: A common safeguard for a data pipeline is redundant computation: derive each published number by two routes built on different technology and refuse to exit when they dis…
- arXiv cs.AIresearchAS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices
arXiv:2609.37617v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by using a smaller drafter to propose tokens for batched verification by a larger target. However, conventional…
- arXiv cs.AIresearchCorrect, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision
arXiv:2609.37624v1 Announce Type: cross Abstract: Fine-tuning a language model on a narrow set of harmful demonstrations, such as bad medical advice, can make it broadly misaligned on unrelated questions, a phenomenon kn…
- arXiv cs.AIresearchSPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving
arXiv:2609.37626v1 Announce Type: cross Abstract: No single way of parallelizing attention serves large language models well under all loads. Low concurrency favors tensor parallelism, many independent requests favor dat…
- arXiv cs.AIresearchProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
arXiv:2609.37632v1 Announce Type: cross Abstract: Time series imputation has progressed from statistical and deep learning approaches to diffusion-based models, which have shown strong recent performance. Existing diffus…
- arXiv cs.AIagentsRLTLDR: Self-improvement by Internalizing Self-generated Feedback
arXiv:2609.37633v2 Announce Type: replace-cross Abstract: The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successfu…
- arXiv cs.AIresearchEvaluating and Benchmarking the System One Model Jev
arXiv:2609.37647v2 Announce Type: replace-cross Abstract: Jev is a commercial "System One" model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed options, a…
- arXiv cs.AIresearchSemantic Map Sharing and Capability-Aware Coverage Planning for AI-Native 6G Robotic Coordination
arXiv:2609.37666v1 Announce Type: cross Abstract: Search and Rescue (SAR) operations increasingly deploy heterogeneous teams of aerial and ground robots. However, conventional coverage methods typically do not translate…
- arXiv cs.AIresearchRetrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection
arXiv:2609.37669v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is increasingly used to enhance Large Language Model (LLM)-based software vulnerability detection by grounding predictions in retriev…
- arXiv cs.AIresearchWhen Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
arXiv:2609.37680v1 Announce Type: cross Abstract: One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can tell us how models pe…
- arXiv cs.AIresearchGARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
arXiv:2609.37694v1 Announce Type: cross Abstract: Diffusion models have recently shown strong potential for probabilistic multivariate time-series forecasting by modeling complex conditional distributions. Recent decoupl…
- arXiv cs.AIresearchWidth Expansion as a Method for Class Incremental Learning
arXiv:2609.37702v1 Announce Type: cross Abstract: Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to past data or task id…
- arXiv cs.AIresearchVIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation
arXiv:2609.37709v1 Announce Type: cross Abstract: Recent multimodal image generation models can take multiple images and textual instructions as input, enabling reference-based generation guided not only by text but also…
- arXiv cs.AIresearchPolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence
arXiv:2609.37712v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, localize, and reason over…
- arXiv cs.AIresearchMulti-Site Real-World Performance of Commercial AI for Pulmonary and Incidental Pulmonary Embolism Detection
arXiv:2609.37750v1 Announce Type: cross Abstract: Pulmonary embolism (PE) is a leading cause of cardiovascular mortality, yet the real-world performance of FDA-cleared AI detection models remains incompletely characteriz…
- arXiv cs.AIresearchHiRAE: Hierarchical Representation Autoencoding with Residual Budgets
arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Meanwhile, intermediat…
- arXiv cs.AIagentsA Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
arXiv:2609.37783v1 Announce Type: cross Abstract: Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to eval…
- arXiv cs.AIresearchA Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
arXiv:2609.37788v3 Announce Type: replace-cross Abstract: We propose a rubric for assessing expressed clinical reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART,…
- arXiv cs.AIresearchPredictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
arXiv:2609.37789v1 Announce Type: cross Abstract: Self-supervised learning (SSL) by predicting in latent space, without generating the input data itself, learns highly abstract, useful representations. Intuitively, this…
- arXiv cs.AIresearchGLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
arXiv:2609.37798v1 Announce Type: cross Abstract: Speech self-supervised learning aims to learn general-purpose representations for downstream speech tasks. However, current approaches rely on complex, carefully designed…
- arXiv cs.AIresearchChallenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation
arXiv:2609.37800v1 Announce Type: cross Abstract: Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two challenges: learning use…
- arXiv cs.AIresearchPixel-Level Transformers in Remote Sensing: A Canopy Height Case Study
arXiv:2609.37809v1 Announce Type: cross Abstract: Predicting canopy height from medium-resolution satellite imagery is a common and scalable approach for assessing the condition of the world's forests, which play a cruci…
- arXiv cs.AIagentsExplore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
arXiv:2609.37810v1 Announce Type: cross Abstract: Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recentl…
- arXiv cs.AIresearchThinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
arXiv:2609.37818v1 Announce Type: cross Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguistic perception and ma…
- arXiv cs.AIagentsMaking Duplicate Reimbursement Unrepresentable: A Verified Ethereum E-Invoice System for Humans and AI Agents
arXiv:2609.37819v1 Announce Type: cross Abstract: Electronic invoices are replacing paper invoices worldwide, but today's centralized architectures leave three problems unsolved on the consumption side: an invoice can be…
- arXiv cs.AIresearchPrivy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR
arXiv:2609.37825v1 Announce Type: cross Abstract: Assigning credit to intermediate steps remains a central challenge in training Large Language Models (LLMs) on multi-step reasoning tasks with sparse terminal rewards, an…