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 226
Long-Horizon RL Needs Muon
Long-horizon agents must coordinate reasoning, tool use, and environment feedback over extended interactions.Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics
Deploying a general-purpose model as an agent means running it inside a product-specific runtime harness that decides which actions are executable, how state advances, and when the loop may terminate.FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning
Client-level fair federated learning, in the form of $q$-fair federated learning ($q$-FFL), agnostic federated learning, or tilted empirical risk minimization, has emerged as an attractive solution…CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing
Large language models (LLMs) have demonstrated multilingual capabilities across diverse language generation and understanding tasks.CASI: Credit Assignment via Set Intervention for Agentic Retrieval
Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulting set.Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence
Vision-Language Models (VLMs) have made substantial progress in spatial reasoning, and self-evolving agents further extend these capabilities to embodied environments by learning from interactions.Beyond Static Cues: Unified Dynamic Detection of MLLM Backdoors via Dual-Flow Trajectory Analysis
Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, yet their susceptibility to backdoor attacks remains a formidable challenge.Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains
Reliable uncertainty estimation is essential for deploying large language models in high-stakes reasoning tasks, yet most existing approaches rely on expensive sampling strategies or shallow…TreeFlex: Agents Navigating Their Own Search Trees
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context.Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning.Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces.Non-asymptotic Convergence of Average-reward Q-learning with Options
We study the finite-sample convergence of Q-learning algorithms for the average-reward formulation of Reinforcement Learning (RL) with options.Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry
Preference optimization ranks final answers and trajectory RL maximizes aggregate returns, yet neither credits the local change that turns a flawed reasoning state into a better one.Human Demonstrations as Post-Training Data for Any Robot Body: Retargeting the Object, Not the Hand
Human demonstrations are today used largely for pretraining vision-language-action models, with little ability to use the same data for target-embodiment or task-oriented training, which scalable…From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation
Large language model (LLM) agents increasingly face tasks from unseen domains and execution contexts, making zero-shot tool selection essential for identifying tools that can satisfy task…Cortex: Consolidating Context into Parametric Memory
Context can improve large language model performance, but these gains may be lost after context removal.When Does Momentum Help in Reinforcement Learning with Verifiable Rewards?
Momentum is a classical tool for accelerating convex optimization and a standard component of modern large language model training.One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM
Poor generalisation in deep neural networks is frequently associated with convergence to sharp minima.From Unreliable to Usable: Decomposing Failure Modes and Confidence Signals in LLM Entity Extraction - Evidence from Cyber Threat Intelligence
Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures actually consist of, and whether confidence…OrionMoE-v1.0: A Mixture-of-Experts Foundation Model for Tabular In-Context Learning
Tabular foundation models enable in-context learning by predicting unseen observations from a labeled support table without task-specific parameter updates.