AI news archive.
19,871 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsDualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning
arXiv:2609.18135v1 Announce Type: cross Abstract: State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. However, existing work…
- arXiv cs.AIresearchMoRE: Mixture of Reused Experts
arXiv:2609.18176v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the numb…
- arXiv cs.AIresearchBeyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers
arXiv:2609.18204v1 Announce Type: cross Abstract: Organizations increasingly use oversight loops where one large language model (LLM) audits another's outputs alongside procedural traces of claimed steps. A common concer…
- arXiv cs.AIresearchCapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026
arXiv:2609.18206v1 Announce Type: cross Abstract: The MUMU track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge requires a single unified multimodal model to jointly solve image tagging (Task A), open…
- arXiv cs.AIresearchA Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification
arXiv:2609.18212v1 Announce Type: cross Abstract: Over the years, Convolutional Neural Networks (CNNs) have demonstrated strong capability in cancer detection and classification using medical images. However, CNN-based m…
- arXiv cs.AIresearchCPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling
arXiv:2609.18216v2 Announce Type: replace-cross Abstract: Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existing approaches…
- arXiv cs.AIresearchAPGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study
arXiv:2609.18219v1 Announce Type: cross Abstract: Quantum Reinforcement Learning (QRL) represents policies as variational quantum circuits (VQCs), making it attractive for combinatorial optimization such as the Capacitat…
- arXiv cs.AIresearchRemembering Solomon Marcus
arXiv:2609.18224v1 Announce Type: cross Abstract: From the manifest of Andre Breton, through the transdisciplinary understanding, we arrive at a post-modern manifest. A talk by Laura De Marco (Harvard) will provide scien…
- arXiv cs.AIresearchQuanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs
arXiv:2609.18248v1 Announce Type: cross Abstract: An advanced retrieval-augmented generation pipeline is typically assembled from three or four independently operated systems: an approximate nearest-neighbour index, a fu…
- arXiv cs.AIresearchM2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models
arXiv:2609.18259v2 Announce Type: replace-cross Abstract: Recent advancements have successfully adapted autoregressive language models to process multimodal signals, such as images and actions. Since raw action signals a…
- arXiv cs.AIresearchI code or AI code: A comparative evaluation of AI-rated scores in classroom observations
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet they remain resource-…
- arXiv cs.AIagentsA Study of the Reliability of Agentic AI-Generated Programs
arXiv:2609.18298v2 Announce Type: replace-cross Abstract: Agentic-AI based software development offers the promise of faster completion of the software, greater programmer efficiency, and more reliable code. The question…
- arXiv cs.AIresearchKnowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering
arXiv:2609.18317v2 Announce Type: replace-cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such as Latin Amer…
- arXiv cs.AIresearchTrajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers
arXiv:2609.18321v2 Announce Type: replace-cross Abstract: Offline on-policy distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same…
- arXiv cs.AIresearchLook Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR
arXiv:2609.18333v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams modeling (DSM) has bec…
- arXiv cs.AIagentsAutonomy in Check: Governor-Mediated Adaptive Security at the Edge
arXiv:2609.18338v1 Announce Type: cross Abstract: Adaptive security at the network edge increasingly relies on automated planners, including rule-based controllers, learned policies, and LLM-assisted agents, that transla…
- arXiv cs.AIresearchSemantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction
arXiv:2609.18368v2 Announce Type: replace-cross Abstract: Classical CSI feedback in FDD massive MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the down…
- arXiv cs.AIresearchGYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models
arXiv:2609.18384v1 Announce Type: cross Abstract: We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains and roles (hence GYR…
- arXiv cs.AIresearchReliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures
arXiv:2609.18396v1 Announce Type: cross Abstract: Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical syste…
- arXiv cs.AIresearchA Non-Linear Neuron Based Detection of Isolated Pixels in Binary and Grayscale Images using Contrast Sensitive Receptive Fields
arXiv:2609.18399v1 Announce Type: cross Abstract: Identifying isolated points is important in image processing applications such as medical imaging, astronomy and quality control management. Other domains, such as cybers…
- arXiv cs.AIresearchTERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting
arXiv:2609.18407v2 Announce Type: replace-cross Abstract: Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, wa…
- arXiv cs.AIresearchMultitask Reinforcement Learning for Assisting Choice Model Specification
arXiv:2609.18441v1 Announce Type: cross Abstract: Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and…
- arXiv cs.AIresearchCSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models
arXiv:2609.18462v5 Announce Type: replace-cross Abstract: FastWAM-style world action models enable efficient action-only inference, but generalize poorly under visual distribution shifts. Their reconstruction-oriented re…
- arXiv cs.AIresearchActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
arXiv:2609.18487v1 Announce Type: cross Abstract: Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the executable commands…
- arXiv cs.AIresearchMiST: Mid-Training LLMs for Cybersecurity
arXiv:2609.18496v1 Announce Type: cross Abstract: Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security…
- arXiv cs.AIresearchVoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval
arXiv:2609.18521v1 Announce Type: cross Abstract: Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing benchmarks and models hav…
- arXiv cs.AIresearchInterpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations
arXiv:2609.18555v1 Announce Type: cross Abstract: Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble membe…
- arXiv cs.AIresearchOn-the-Fly Homographies Calibration for Multi-Camera Tracking
arXiv:2609.18582v1 Announce Type: cross Abstract: Precise multi-camera tracking traditionally relies on rigorous 3D site calibration, yet this requirement is often operationally impossible in large-scale deployments. Pri…
- arXiv cs.AIresearchLabel-free steering: Compressing test-time reinforcement learning into bias-only subspaces
arXiv:2609.18587v3 Announce Type: replace-cross Abstract: Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically opti…
- arXiv cs.AIagentsHypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents
arXiv:2609.18598v1 Announce Type: cross Abstract: Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the output is a set of op…
- arXiv cs.AIresearchOnline Robust Reinforcement Learning Through Monte-Carlo Planning
arXiv:2609.18599v1 Announce Type: cross Abstract: Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real…
- arXiv cs.AIagentsPACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
arXiv:2609.18605v1 Announce Type: cross Abstract: As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such as hiring, healthcare, and finance. In these conte…
- arXiv cs.AIresearchGenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media
arXiv:2609.18634v1 Announce Type: cross Abstract: Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports, performance, or int…
- arXiv cs.AIagentsCoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning
arXiv:2609.18639v1 Announce Type: cross Abstract: Emergency management assistance programs, such as relief distribution, are essential for delivering necessary supplies to affected communities. However, these programs op…
- arXiv cs.AIresearchBeyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification
arXiv:2609.18673v1 Announce Type: cross Abstract: Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluations often reduce priva…
- arXiv cs.AIresearchGeneralist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging
arXiv:2609.18688v1 Announce Type: cross Abstract: AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (…
- arXiv cs.AIresearchEcho: Learning-based Matching Decompilation using Trusted Back Translation
arXiv:2609.18706v1 Announce Type: cross Abstract: Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompilation addresses this…
- arXiv cs.AIresearchRethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
arXiv:2609.18708v1 Announce Type: cross Abstract: In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy…
- arXiv cs.AIresearchA Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages
arXiv:2609.18739v1 Announce Type: cross Abstract: Poor quality or noisy annotations in Named Entity Recognition (NER), as in any other NLP task, make it challenging to achieve state-of-the-art performance. In this paper,…
- arXiv cs.AIagentsProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
arXiv:2609.18805v1 Announce Type: cross Abstract: Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents may need to infer beha…
- arXiv cs.AIresearchUsing OCR Heads to Verbalize Image Semantics
arXiv:2609.18823v1 Announce Type: cross Abstract: How do VLMs map from pixels to semantics? To understand this general question, we focus on a narrow one: studying how VLMs perform optical character recognition (OCR). Ac…
- arXiv cs.AIagentsAsk the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It
arXiv:2609.18849v1 Announce Type: cross Abstract: An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whether that cache stays…
- arXiv cs.AIresearchGrainSpeech: Less Context, More Detail for Compact Speech Synthesis
arXiv:2609.18856v1 Announce Type: cross Abstract: Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram supervision. A recep…
- arXiv cs.AIagentsTaming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN
arXiv:2609.18857v1 Announce Type: cross Abstract: The O-RAN control plane is becoming agentic: autonomous AI agents, deployed as rApps by different vendors, independently close control loops over shared radio resources.…
- arXiv cs.AIresearchDecodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
arXiv:2609.18860v2 Announce Type: replace-cross Abstract: When large vision-language models misclassify harmful memes, the failure may reflect missing internal evidence or an inability to route represented evidence to th…
- arXiv cs.AIagentsASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions
arXiv:2609.18864v2 Announce Type: replace-cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unauthorized expo…
- arXiv cs.AIresearchNeuroECG: ECGFounder-Based Deep ECG Representation for EEG-Free Neurological Prognostication After Cardiac Arrest
arXiv:2609.18891v2 Announce Type: replace-cross Abstract: Neurological prognostication after cardiac arrest commonly relies on electroencephalography (EEG). However, EEG demands high clinical resources. Bedside electroca…
- arXiv cs.AIagentsBeyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking
arXiv:2609.18909v2 Announce Type: replace-cross Abstract: Agent benchmarks are substantially more costly to evaluate than conventional LLM benchmarks. Benchmark compression is therefore a natural solution, yet existing m…
- arXiv cs.AIresearchHigher-order pruning of experts in mixture-of-experts language models
arXiv:2609.18916v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct appro…
- arXiv cs.AIagentsSocial Laws for Multi-agent Coordination in Stochastic Environments
arXiv:2609.18929v1 Announce Type: cross Abstract: In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous research on social law…