AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsBridging Static and Agentic RAG for Taiwanese Historical Question Answering
arXiv:2609.23056v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) enables language models to adapt retrieval based on previously retrieved evidence, but it remains unclear whether such adapti…
- arXiv cs.AIagentsSkip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files
arXiv:2610.21073v1 Announce Type: cross Abstract: A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patch…
- arXiv cs.AIresearchWhere Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning
arXiv:2610.32951v1 Announce Type: cross Abstract: Reinforcement learning for large language models often uses separate systems for inference and training. Even with identical weights and BF16 tensors, implementation diff…
- arXiv cs.AIagentsLLM-Augmented Agent-Based Simulation of Cyber Social Agents
arXiv:2610.32988v1 Announce Type: cross Abstract: Social media bots are often portrayed as malicious automations to be detected and removed, but automation on social media platforms encompasses a wide spectrum of roles,…
- arXiv cs.AIresearchDairySocialTwin: Auditing the video-to-graph evidence chain in cattle social networks
arXiv:2610.32989v1 Announce Type: cross Abstract: Video-derived social graphs can appear precise while inheriting uncertainty from detection, tracking, classification, and aggregation. We present DairySocialTwin, a graph…
- arXiv cs.AIagentsTIAgent: From Natural Language to Grounded Agentic Workflows for Computational Pathology
arXiv:2610.32993v1 Announce Type: cross Abstract: Computational pathology (CPath) analyses increasingly depend on multi-step computational workflows that require substantial programming expertise, limiting their accessib…
- arXiv cs.AIresearchWhispering Wisely: Smart Subset Selection for ASR Fine-Tuning
arXiv:2610.32997v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) models such as OpenAIs Whisper have substantially improved speech recognition quality but remain expensive to fine-tune, especially whe…
- arXiv cs.AIresearchEntity-Aware Evaluation of OCR Systems for Historical Document Transcription
arXiv:2610.33004v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily…
- arXiv cs.AIresearchTraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models
arXiv:2610.33008v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) enable flexible generation through iterative masked denoising, but incur substantial inference cost because token representations…
- arXiv cs.AIagentsRADAgent: Automating RADseq Pipelines with Private Open-Source LLMs
arXiv:2610.33009v1 Announce Type: cross Abstract: Restriction site-associated DNA sequencing (RADseq) is a family of reduced-representation sequencing methods. It uses restriction enzymes to sample subsets of the genome,…
- arXiv cs.AIagentsWhen Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems
arXiv:2610.33011v1 Announce Type: cross Abstract: While recent advances in autonomous agents enable them to coordinate on increasingly complex tasks, prior work shows that this growing capacity for coordination can creat…
- arXiv cs.AIagentsRecursive Semantic Divergence for LLM Agent Consistency
arXiv:2610.33012v1 Announce Type: cross Abstract: Large Language Model (LLM) agents with tool use exhibit inconsistent behavior across independent runs from identical states, calling different tools, producing contradict…
- arXiv cs.AIagentsUMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
arXiv:2610.33013v1 Announce Type: cross Abstract: Multi-Agent Systems (MAS) are a promising paradigm for improving the reasoning capabilities of large language models, yet they remain prone to hallucinations and erroneou…
- arXiv cs.AIagentsThe Social World Model Evaluation Gap
arXiv:2610.33014v1 Announce Type: cross Abstract: A negotiation assistant can reach a good deal without accurately predicting the other person's response. We ask whether evaluations of social world models test that predi…
- arXiv cs.AIagentsSLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory
arXiv:2610.33015v1 Announce Type: cross Abstract: Long-term memory enables large language model (LLM) agents to maintain personalized and temporally coherent interactions, but repeated LLM inference for memory admission,…
- arXiv cs.AIresearchMerge-Based Vocabulary Extension Stalls at the Pre-Tokenizer: An English-Preserving Repair for Nepali, Tested in Continued Pretraining
arXiv:2610.33016v1 Announce Type: cross Abstract: Llama-3, Qwen3 and many other open LLMs pre-tokenize text with a regular expression whose word class admits only Unicode letters. Devanagari vowel signs are combining mar…
- arXiv cs.AIagentsSUDO: From Scientific Publications to Global Scholarly Discourse
arXiv:2610.33018v1 Announce Type: cross Abstract: Scholarly Knowledge Graphs (SKGs) support literature search, scientific discovery, and agent-assisted research. Yet, most approaches to SKG construction pre-specify the k…
- arXiv cs.AIresearchMine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own
arXiv:2610.33020v1 Announce Type: cross Abstract: If your brain were connected directly to someone else's, would you still know which thoughts were yours? We build a functional version with two copies of one language mod…
- arXiv cs.AIagentsEvolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
arXiv:2610.33024v1 Announce Type: cross Abstract: Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiveness depends on whethe…
- arXiv cs.AIresearchConceptizer: Next-Token Prediction Is Not All You Need
arXiv:2610.33027v1 Announce Type: cross Abstract: Next-token prediction (NTP) rewards only the token that occurs next, penalizing every alternative. But natural language often offers many ways to express the same meaning…
- arXiv cs.AIagentsLessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision?
arXiv:2610.33029v1 Announce Type: cross Abstract: Self-improving agents write lessons from the outcomes of their runs; when outcomes are noisy, a lesson can carry chance into later decisions. We measure one link of this…
- arXiv cs.AIresearchFeature Scaling Beats Architecture Choice in Offline Respiratory Screening for Low-Resource Clinics
arXiv:2610.33030v1 Announce Type: cross Abstract: Deep models are the usual choice for respiratory sound classification, but in clinics without GPUs or connectivity that choice carries a cost. We compare classical and de…
- arXiv cs.AIresearchA Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models
arXiv:2610.33036v2 Announce Type: replace-cross Abstract: Speaking-style captioning (SSC) aims to generate natural language descriptions of how speech is delivered, capturing paralinguistic attributes such as vocal timbr…
- arXiv cs.AIagentsParametric Session States Recover Retrieval Intent without Replaying History
arXiv:2610.33047v1 Announce Type: cross Abstract: Long-running assistants often interpret follow-up requests whose referents, constraints, and active goals were established many turns earlier. The central challenge is th…
- arXiv cs.AIresearchGMoE-FTI: A Universal Facial Template Inversion Method Adopting Genuine Mixture-of-Experts Mechanism
arXiv:2610.33055v1 Announce Type: cross Abstract: Face recognition systems have been ubiquitously deployed across daily scenarios. To protect user privacy, mainstream systems store facial templates rather than raw face i…
- arXiv cs.AIresearchAerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs
arXiv:2610.33056v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) have revolutionized general visual perception, existing methods suffer from severe hallucination in the aerial domain, wher…
- arXiv cs.AIresearchDRA-SAM: Disagreement-Driven Referential Active SAM for Low-Altitude Drone Referring Segmentation
arXiv:2610.33057v1 Announce Type: cross Abstract: Referring segmentation in low-altitude drone imagery requires distinguishing small, visually similar instances under complex linguistic and spatial constraints. Global in…
- arXiv cs.AIresearchKDHNet: A Knowledge-Driven Hybrid Network for Limited-Calibration SSVEP Decoding
arXiv:2610.33058v1 Announce Type: cross Abstract: Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) achieve high information transfer rates but often require sufficient subject-specific…
- arXiv cs.AIresearchMOSAIC: Towards a Universal Latent Space for Computational Pathology Foundation Models
arXiv:2610.33059v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) differ substantially in architecture, pretraining objective, training data and representation dimensionality, yet it remains unclear wh…
- arXiv cs.AIresearchMARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation
arXiv:2610.33060v1 Announce Type: cross Abstract: Generating an articulated object from images and text requires more than plausible parts and movable joints: the assembled mechanism must execute the intended motion. Thi…
- arXiv cs.AIresearchOddin: Latent Visual Reasoning in Unified Multimodal Models via Self-Distillation from Image Generation
arXiv:2610.33062v1 Announce Type: cross Abstract: Unified large multimodal models (ULMMs) are able to perform visual reasoning through interleaved text-image generation, but generating explicit intermediate images incurs…
- arXiv cs.AIresearchA Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures
arXiv:2610.33063v1 Announce Type: cross Abstract: Deployed vision models auto-accept confident predictions, so high-confidence errors propagate silently. Maximum Softmax Probability (MSP), the standard failure predictor,…
- arXiv cs.AIresearchProtoEEG: Structured Prototype Alignment for EEG Visual Decoding
arXiv:2610.33065v1 Announce Type: cross Abstract: EEG visual decoding remains difficult because scalp recordings are noisy, spatially coarse, and variable across trials and subjects. Most systems align each trial with a…
- arXiv cs.AIresearchPhaseBreak: Proactive Temporal Protection against Unauthorized Image-to-Video Animation
arXiv:2610.33070v1 Announce Type: cross Abstract: Image-to-Video (I2V) diffusion models can animate a single portrait or photograph, enabling shared images to be repurposed for motion synthesis without the subject's auth…
- arXiv cs.AIresearchVLMProbe: An Open-source Library for VLM Probing and Interpretation
arXiv:2610.33072v1 Announce Type: cross Abstract: Understanding how vision-language models use visual information requires connecting internal representations to model behavior. We present vlmprobe, an open-source librar…
- arXiv cs.AIresearchAGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models
arXiv:2610.33074v1 Announce Type: cross Abstract: Vision-language-action (VLA) models enable robots to perform tasks specified through natural-language instructions, but their large weight footprint challenges deployment…
- arXiv cs.AIresearchDiagnosing and Mitigating Evidence Misgrounding in Multimodal Knowledge Editing
arXiv:2610.33075v1 Announce Type: cross Abstract: Multimodal knowledge editing aims to update visually grounded facts in Multimodal Large Language Models (MLLMs) while preserving unrelated text and visual behaviors. Howe…
- arXiv cs.AIresearchEvaluating Visual Language Models on Visual Grounding for Visually Impaired People
arXiv:2610.33078v2 Announce Type: replace-cross Abstract: Visual grounding (VG) in visual question answering (VQA) is a fundamental capability of Vision-Language Models (VLMs), enabling the detection of the most relevant…
- arXiv cs.AIresearchAnalogPortBench: Benchmarking LLMs on Analog Circuit Porting
arXiv:2610.33088v1 Announce Type: cross Abstract: Analog circuit design still relies heavily on expert knowledge, and porting proven designs to new process nodes is a recurring bottleneck. As a lower supply reduces avail…
- arXiv cs.AIresearchBeyond Correctness: Attribution of Natural-Language Documentation for Formal Libraries
arXiv:2610.33094v1 Announce Type: cross Abstract: Formal languages are widely used in software engineering to specify and verify program properties. Because their mathematical notation and logic are hard to read, develop…
- arXiv cs.AIresearchEGGPlacer: Energy-Guided Generative Chip Placement with Diffusion Models
arXiv:2610.33099v1 Announce Type: cross Abstract: Chip placement strongly affects routed wirelength and thermal behavior, yet these downstream metrics are difficult to evaluate during macro placement. Learning-based macr…
- arXiv cs.AIresearchWhale You Go Green? Immediate and Longitudinal Effects of Embodied Conversational AI Avatars on Sustainable Behavioral Tendencies and Pro-Environmental Attitudes
arXiv:2610.33191v1 Announce Type: cross Abstract: Embodied conversational AI can be persuasive, but can it motivate people to develop sustainable behavioral tendencies and increase pro-environmental attitudes? We conduct…
- arXiv cs.AIagentsCross-Platform Application Migration to HarmonyOS: An Agentic Pipeline with Artifact-Derived Verification
arXiv:2610.33197v1 Announce Type: cross Abstract: The migration of applications written for a different platforms like Android or iOS to HarmonyOS NEXT requires a complete rewrite in ArkTS. Although LLMs automate the tra…
- arXiv cs.AIagentsPosition, Role or Label? A Controlled Study of Instruction Conflicts in LLM Agents
arXiv:2610.33201v1 Announce Type: cross Abstract: LLM agents take instructions from the operator, repository configuration, user, tool results and saved memory, which often conflict. Instruction-hierarchy benchmarks ask…
- arXiv cs.AIagentsOperationalizing Governed Agentic Workflows in Regulated Finance: A Customer Zero Case Study using Zafin AIOS
arXiv:2610.33253v1 Announce Type: cross Abstract: Regulated industries such as finance and healthcare face critical governance challenges that hamper the adoption of AI-assisted software development and hinder the transi…
- arXiv cs.AIresearchImage Clustering with Vision-Language Model Embeddings
arXiv:2610.33265v1 Announce Type: cross Abstract: Pretrained vision-language models provide image representations whose suitability for clustering may vary with feature extraction, image domain, and partitioning algorith…
- arXiv cs.AIresearchThe As-If Machine: Personalized counterfactuals make distant policy risks feel close
arXiv:2610.33301v1 Announce Type: cross Abstract: Life experiences can shape policy attitudes, but we only live one life. Citizens may therefore fail to support policies addressing risks they have never personally experi…
- arXiv cs.AIresearchExploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns
arXiv:2610.33310v1 Announce Type: cross Abstract: Powder X-ray diffraction (XRD) is the primary high-throughput method for resolving crystal structures, a cornerstone of materials science. As high-throughput synthesis an…
- arXiv cs.AIresearchWhen Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training
arXiv:2610.33311v1 Announce Type: cross Abstract: How does pre-trained model capacity relate to performance after adaptation for causal tasks? We study two systems built on the Qwen 2.5 family: CausalLLM, which estimates…
- arXiv cs.AIagentsResponsibility Boundaries for Agentic Systems: A Comparative Evaluation of Probabilistic Agentic Programming
arXiv:2610.33312v1 Announce Type: cross Abstract: Language-model agents combine reasoning, tools, memory, delegation, and external effects. Authority is often distributed across prompts, host code, configuration, and log…