AI & Machine Learning · Computer Science & AI
Artificial Intelligence
The newest papers in Artificial Intelligence that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 6 November 2026: 4,992 arXiv preprints and 8 OpenAlex records.
Get the few papers worth your time in Artificial Intelligence every morning.
Follow Artificial Intelligence and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 225
Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution
Graphical user interface (GUI) agents now execute workflows across real applications, but when execution drifts, users must determine what changed, what should have remained untouched, and what can…From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias
Prior work on implicit bias shows that gradient descent selects the Frobenius max-margin direction on linearly separable problems, whereas Fan et al. (2025) established spectral max-margin behavior…ACR-Net: Mitigating Semantic Dominance via Contrastive Acoustic-Semantic Decoupling
Speech Emotion Recognition (SER) models and Audio LLMs fail when vocal tone contradicts textual semantics.Maximising Transparency in Context Compaction Improves Retention of Facts and Commitments for Lightweight Coding Agents
Long coding agent sessions outgrow the model's context window, so agents compact: older history is replaced by something shorter, usually a model-written summary.DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing
Human mesh recovery (HMR) provides a geometric foundation for understanding human motion, but accurately reconstructing both body motion and fine hand articulation from videos remains challenging…LLM-Based Policy Compliance Verification of Loan Applications
Banks rely on extensive internal policy frameworks to ensure that corporate lending decisions comply with regulatory requirements and internal risk standards.MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue
Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel without taking it.Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode.Value-Guided Repulsion for Offline Reinforcement Learning
Drifting models have emerged as a highly efficient and stable paradigm for policy design in offline reinforcement learning (RL).HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation
Medication recommendation (MR) is critical for clinical decision support.SWE-Stream: Scaling Executable Training Data for SWE Agents via Progressive Construction and Elastic Streaming
Software engineering agents have advanced rapidly, but scaling their training remains constrained by the limited availability of high-quality executable tasks.What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds
Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances.Drivers of LLM Consensus Formation Under Competing Incentives: A Simulation Study
Large Language Models (LLMs) are increasingly deployed in multi-agent environments that produce unanimous agreement, both in intended interactions that need coordination and in unintended emergent…What and Where in Identifying and Quantifying Conventions in Humans and AI Agents
Cooperative success rests in part on implicit communication.Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties
Counterfactual reasoning (asking what would have happened, had a decision been different) is a powerful tool for identifying causes of failure and explaining the behaviour of AI systems in…Scaling Multilingual Safety and Reasoning Evaluation through Reasoning-Guided Translation
Large language models (LLMs) are increasingly deployed across languages, yet their safety and reasoning capabilities remain predominantly evaluated in English.Design Space Exploration of Reinforcement Learning Configurations for Post-Legalization Placement
Graph Neural Networks (GNNs) and Reinforcement Learning (RL) have recently been explored for VLSI placement optimization, but their effectiveness for post-legalization placement refinement remains…PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents
A multiplayer world model must predict how the independent actions of several players change a shared environment, including changes outside a player's current field of view.Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications.P2Patch: Exploit-Guided Vulnerability Repair
Large language models are increasingly deployed as autonomous agents for automated program repair, patching software vulnerabilities through multi-step reasoning and tool use.