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 11 October 2026 to 5 November 2026: 4,998 arXiv preprints and 2 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 144
High-Value Training Data from Noisy, Diverse Sources
Training state-of-the-art models increasingly requires learning from large, heterogeneous datasets whose examples vary in quality, domain relevance, and source of supervision.RoleFlow: Self-Evolving Multi-Role Agentic Collaboration via Structural Adaptation
Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements.Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information.Secure Agentic AI and Multimodal Intelligence in 6G Communication Systems
Sixth-generation (6G) communication systems are expected to support immersive, intent-driven, and latency-critical services through tight integration of multimodal intelligence, edge computing, and…SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning
Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL).A Three-Pillar Governance Framework for Safe and Trustworthy AI Agents
AI agents capable of autonomous decision-making introduce significant challenges related to safety, alignment, accountability, and human oversight.Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning
Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one.aggmetrics: Aggregating Classification Performance Measures for Machine Learning
aggmetrics is a Python package that extends any binary performance measure expressed in the four confusion-matrix counts to multiclass, multilabel, ordinal, cost-sensitive, soft-label and…Short-to-Long: Detached Features for Long-Horizon Value Learning
Learning useful representations from continually changing value targets remains a challenge in deep reinforcement learning.SplatLab: Autonomous Scientific Discovery for 3DGS Research
Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed.Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
Sparse autoencoders (SAEs) were originally motivated by discovering monosemantic features, a property that characterizes individual features but does not specify what the learned feature set should…Externalise the Memory: A Pre-Registered Study of Where an Embodied Agent's Experience Should Live
Should an embodied agent's experience be baked into its policy weights, or kept external and retrieved at inference?Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences
Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction…From Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?
World models help agents assess the consequences of their actions before acting.What the Trace Shows and What the Label Says: Auditing Behavioral Detectors in Agent Evaluation
LLM agents are often evaluated by reducing execution traces to labels such as final-answer correctness, tool verification, and fault propagation.From Prose to Properties: Testing Research Claims with ARATest for Agent-Native Science
AI agents now run experiments and report findings, so research produces claims faster than researchers can check them.Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3
A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task.PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization
Motion Diffusion Models (MDMs) can generate diverse and visually appealing human motion; yet, the resulting trajectories frequently violate physical constraints, limiting their downstream use in…Behind Aggregate Scores: What Systematically Varying Arena-Hard's LLM Judge Reveals
LLM judges are used to determine which of two answers is better.Protegrity-PII Technical Report
We present Protegrity-PII, a new PII decision model for structured and unstructured text.