AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchStaged Continual Adaptation of Multimodal Foundation Models for Japanese Financial Documents
arXiv:2610.27904v1 Announce Type: new Abstract: Staged post-training of multimodal foundation models chains vision-language alignment, reasoning distillation, and domain tuning, yet how each phase trades capabilities aga…
- arXiv cs.AIagentsMMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
arXiv:2610.27911v1 Announce Type: new Abstract: Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats,…
- arXiv cs.AIresearchACE-Compression: An Ability-Centric Evaluation of Compressed Large Language Models
arXiv:2610.27913v1 Announce Type: new Abstract: Model compression makes large language models deployable, but today's evaluation tells an incomplete story. Standard practice measures retained task performance and stops t…
- arXiv cs.AIresearchQuantum-JEPA: Quantum Born Priors for Latent-Action JEPA World Models
arXiv:2610.27921v1 Announce Type: new Abstract: A single observation can admit several plausible futures, making uncertainty an essential part of world modelling. However, quantum generative models remain underexplored f…
- arXiv cs.AIresearchFrom Comparison to Selection: Enhancing Cross-Scale Generalization of Pointer Networks Trained with Reinforcement Learning for Capacitated Vehicle Routing Problem
arXiv:2610.27936v3 Announce Type: replace Abstract: Vehicle routing in delivery and logistics remains challenging as the number of clients varies. Classical approaches based on mixed-integer programming and heuristics ca…
- arXiv cs.AIresearchHypTI: Hyperbolic Geometry-Aware Multimodal Feature Fusion Framework for Dementia Detection Based on Tabular-Image Data
arXiv:2610.27941v1 Announce Type: new Abstract: AI-assisted dementia detection usually requires multimodal fusion of diverse data, such as clinical tabular assessments and neuroimaging data. However, most existing approa…
- arXiv cs.AIagentsLost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
arXiv:2610.27954v1 Announce Type: new Abstract: Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However,…
- arXiv cs.AIagentsWhen Do Humans and Machines Truly Complement Each Other? Formal Conditions and Empirical Evidence for Human-AI Synergy
arXiv:2610.27965v1 Announce Type: new Abstract: Can humans and artificial intelligence cooperate such that their combination yields greater accuracy than either agent alone? This result, termed \emph{synergy} or \emph{co…
- arXiv cs.AIresearchBuilding Telecom Language Models with RSOD: Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking Evaluation
arXiv:2610.27993v1 Announce Type: new Abstract: Telecom language models must combine broad networking knowledge with specialist behavior across routing, broadband services, access technologies, and operational diagnostic…
- arXiv cs.AIresearchDancing Diffusion: Learning Continuous Programs for Image Generation and Editing
arXiv:2610.28003v2 Announce Type: replace Abstract: Diffusion models generate samples through a multi-step denoising trajectory, yet condition every step on the same instruction, so the trajectory cannot be addressed at…
- arXiv cs.AIresearchTrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment
arXiv:2610.28060v1 Announce Type: new Abstract: The Reinforcement Learning (RL) paradigm has achieved remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, when applied to l…
- arXiv cs.AIresearchSlot-JEPA: Object-Structured Prediction Interfaces for Latent World Models
arXiv:2610.28074v1 Announce Type: new Abstract: As a prototypical latent world model, Joint-Embedding Predictive Architectures (JEPAs) provide strong semantic representations. However, dense patch representations expose…
- arXiv cs.AIresearchIECG: Weakly-Supervised Interpretability-Enhancing Foundation Model for Electrocardiogram
arXiv:2610.28083v1 Announce Type: new Abstract: Electrocardiography (ECG) is a cornerstone of cardiac diagnosis, yet most machine learning methods for ECG analysis lack interpretability, limiting their clinical adoption.…
- arXiv cs.AIresearchInsightRAG: Aggregating Distributed Scholarly Judgments for Scientific Survey Generation
arXiv:2610.28085v1 Announce Type: new Abstract: The rapid growth of scientific literature makes survey writing increasingly challenging, motivating automatic survey generation. Yet, existing systems must search an open s…
- arXiv cs.AIresearchPolyscene: Scenario Planning as Diversity Planning
arXiv:2610.28102v1 Announce Type: new Abstract: Scenario planning is a foresight practice in which analysts construct a small set of plausible futures and prepare an organisation for each. Each scenario is a narrative th…
- arXiv cs.AIresearchA Semi-Analytical Inference Framework for Structural Causal Models
arXiv:2610.28103v1 Announce Type: new Abstract: Structural Causal Models (SCMs) provide a principled framework for observational, interventional, and counterfactual reasoning, all of which rely on probabilistic inference…
- arXiv cs.AIresearchRobust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck
arXiv:2610.28110v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) have shown great potential for low-power neuromorphic computing due to their event-driven processing and spatiotemporal sparsity, but they re…
- arXiv cs.AIagentsInterruption-Aware Recurrent Reinforcement Learning for UAS Navigation Under Temporary Overrides
arXiv:2610.28121v1 Announce Type: new Abstract: Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial o…
- arXiv cs.AIagentsMaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses
arXiv:2610.28201v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching th…
- arXiv cs.AIagentsChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart Reasoning
arXiv:2610.28282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. Whil…
- arXiv cs.AIresearchIs Sycophancy a Form of In-Context Updating?
arXiv:2610.28325v1 Announce Type: new Abstract: Factual sycophancy, a language model's deference to a user's false beliefs, is usually understood as a bid for the user's approval at the expense of truthfulness. We argue…
- arXiv cs.AIagentsS-Agent 2.0: Spatial Reasoning with a General Coding Agent
arXiv:2610.28354v1 Announce Type: new Abstract: Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improv…
- arXiv cs.AIagentsFALCA: Falsification-Aware Reinforcement Learning with Hierarchical Credit Assignment for Long-Horizon Deep Search Agents
arXiv:2610.28361v1 Announce Type: new Abstract: Long-horizon deep search requires LLM agents to iteratively decompose complex information needs, gather evidence from external sources, and maintain a reliable research sta…
- arXiv cs.AIresearchRACE: RoPE-Aligned Attention Compression Based on Query-Key Activation Energies
arXiv:2610.28385v1 Announce Type: new Abstract: Head-dimension compression can reduce the memory required by the key-value (KV) cache, but existing methods often reconstruct full-dimensional representations during infere…
- arXiv cs.AIresearchDIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams
arXiv:2610.28405v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have substantially improved spoken interaction and video understanding. Existing online and streaming benchmarks…
- arXiv cs.AIresearchStratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
arXiv:2610.28441v1 Announce Type: new Abstract: Large Language Model inference over long contexts is increasingly bottlenecked by the cost of attending to a growing Key-Value (KV) cache. Sparse attention reduces this cos…
- arXiv cs.AIagentsToolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
arXiv:2610.28454v1 Announce Type: new Abstract: Agents are starting to sell to other agents. Seller agents write the listings of tools, services and products, and buyer agents read these listings when they choose what to…
- arXiv cs.AIresearchBeyond Trajectory Statistics: Community-Consistent Human Mobility Generation via Evolving User-Location Graphs
arXiv:2610.28467v2 Announce Type: replace Abstract: Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajectories when real dat…
- arXiv cs.AIagentsClaims of emergence in AI should be grounded in information decomposition
arXiv:2610.28479v1 Announce Type: new Abstract: When a language model develops capabilities not traceable to its individual components, when a multi-agent AI system outperforms each agent on its own, or when a human-AI p…
- arXiv cs.AIresearchExploring Temporal Context-Aware Physical Grounding in Latent World Models
arXiv:2610.28483v1 Announce Type: new Abstract: Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive Architectures (JEPAs)…
- arXiv cs.AIagentsProof-Carrying Contracts: Commitments AI Agents Cannot Break
arXiv:2610.28484v1 Announce Type: new Abstract: AI agents increasingly act on behalf of people or other agents, purchasing services, exchanging information and delegating work. What an agent must respect is written in in…
- arXiv cs.AIresearchDecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
arXiv:2610.28522v1 Announce Type: new Abstract: Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions acr…
- arXiv cs.AIresearchBeyond 4 bits: Data-Centric Post-training Quantization and Recovery
arXiv:2610.28537v1 Announce Type: new Abstract: Post-training quantization (PTQ) compresses the weights of a trained model with limited compute and data. Down to 4 bits it is near-lossless, but at 2 bits scalar PTQ confi…
- arXiv cs.AIresearchHumans Correct Their Judgments Through Debate, but Weaker AI Models Do Not
arXiv:2610.28539v1 Announce Type: new Abstract: How can we effectively oversee AI systems that surpass human intelligence? AI Safety via Debate proposes that two AI systems argue opposing positions and a judge, either a…
- arXiv cs.AIagentsAgentic Ensemble with Vision-Language Models for Visual Anomaly Detection
arXiv:2610.28560v1 Announce Type: new Abstract: Visual anomaly detection aims to detect abnormal objects, while anomaly samples are often scarce during model training. Assembling multiple pretrained detectors can help by…
- arXiv cs.AIresearchOptScientist: Automated Discovery of Optimization Laws
arXiv:2610.28562v1 Announce Type: new Abstract: Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused on recovering equation…
- arXiv cs.AIresearchEvolving Semantic Indexes for Generative Retrieval
arXiv:2610.28568v1 Announce Type: new Abstract: Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs). SID design largely determines GR quality, bu…
- arXiv cs.AIagentsSage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
arXiv:2610.28578v1 Announce Type: new Abstract: In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composi…
- arXiv cs.AIresearchBeyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal Reasoning
arXiv:2610.28584v1 Announce Type: new Abstract: Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) offer parallelism but lack semantic coherence. To addres…
- arXiv cs.AIresearchWhat Do RTL Repair Benchmarks Actually Measure?
arXiv:2610.28595v1 Announce Type: new Abstract: RTL repair benchmarks should measure whether a model can fix broken RTL given a specification. To this end, we construct and hash-bind RTLRepairDataset, 5,784 (broken, fixe…
- arXiv cs.AIagentsEvolving Agent Interfaces
arXiv:2610.28601v1 Announce Type: new Abstract: Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thous…
- arXiv cs.AIresearchValue-Rich, Differently Organized: Measuring Value Expression and Organization in AI-Generated Debates
arXiv:2610.28604v1 Announce Type: new Abstract: Current evaluation of LLM-generated debate largely focuses on argumentative quality, leaving the value structure of generated arguments underexamined. We introduce a diagno…
- arXiv cs.AIagentsSemantic Observability for Autonomous Systems Diagnostics
arXiv:2610.28611v1 Announce Type: new Abstract: Modern distributed microservice deployments generate massive volumes of heterogeneous, multi-format observability logs across physically and logically partitioned infrastru…
- arXiv cs.AIresearchAdaptive Multi-Token Prediction: How far should we go?
arXiv:2610.28619v1 Announce Type: new Abstract: Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculati…
- arXiv cs.AIagentsLarge Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle
arXiv:2507.05723v1 Announce Type: cross Abstract: The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked interest in the Agent…
- arXiv cs.AIagentsINCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models
arXiv:2606.23571v2 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into first-principles computational workflows, yet their ability to configure scientific calculations remai…
- arXiv cs.AIresearchFine-Tuning Small Language Models for Reliable VASP INCAR Generation
arXiv:2608.05387v1 Announce Type: cross Abstract: Language models can prepare VASP INCAR files from natural-language requests, but so far only large proprietary cloud models come close to handling the tightly coupled, ph…
- arXiv cs.AIagentsAptamers as a sandbox for lab-in-the-loop agentic molecular discovery
arXiv:2610.24806v1 Announce Type: cross Abstract: Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for validation rather than…
- arXiv cs.AIagentsMeasuring Consensus in AI Agent Networks
arXiv:2610.24833v1 Announce Type: cross Abstract: As AI agents become increasingly connected through networks and take on tasks that require negotiation and joint decision-making, a systematic approach is needed to asses…
- arXiv cs.AIresearchDisentangling Depression from Cognitive Decline in Elderly Speech Using Concurrent Clinical Assessments
arXiv:2610.26890v1 Announce Type: cross Abstract: Detecting depression from speech in elderly patients with mild cognitive impairment (MCI) is complicated by overlapping acoustic effects of cognitive decline. Without dis…