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 114
More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents
Self-evolving training improves the performance of agents on difficult tasks through verifiable feedback, but it often applies costly deliberation uniformly across tasks.PACE: Research Proving Agent for Adaptive Conjecture Exploration
Many mathematical research agents focus on solving problems with fixed statements.Embedding-Based Educational Taxonomies
Educational taxonomies organize educational content, such as exercise problems, into concepts, which are also called skills or knowledge components.Seeing the Options: Typed Decisions over Visual Candidates with Reusable Option Memory
Agents end many steps in a typed decision over a set of candidates: which screen element to click, which product to pick.E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges
Depth boundaries remain a major source of error in stereo matching.Human-Feedback-Guided Multi-Agent Inverse Reinforcement Learning for Interactive Driving Behavior Modeling
Modeling human driving behavior is fundamental to understanding driver decision-making and supporting autonomous vehicles (AVs) in mixed traffic.Strategic Calibration in LLM Multi-Agent Systems: Audited Pivot Scoring for Truthful Elicitation
In large language model (LLM)-based multi-agent systems, reported confidence increasingly determines the allocation of scarce downstream attention, computation, and decision influence.Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Generative AI and large language models (LLMs) are moving into the Internet of Things, yet most deployments assume cloud connectivity, and many IoT settings have intermittent, restricted, or no…A Distribution-Matching Perspective on LLM Training Algorithms
In this work, we propose a unified framework for training algorithms across different stages of modern large language model development, based on the perspective of distribution matching.POD-RoPE: Rotary Position Encoding over Physical Observation Distributions for Embodied AI
Embodied perception requires positional representations that capture both physical geometry and the spatial and temporal extent of observations.ProtAgent: Post-Training Compact Protein Tool Agents with Interaction-Level Credit Assignment
Protein annotation agents must choose suitable bioinformatics tools, interpret their outputs, and use the resulting evidence in the final answer.C-DFF: Concept-Level Diagnostics for Mechanism Parity in Simulation-Based Validation of Autonomous Driving Perception
Simulation is widely used in autonomous-driving validation, but matching task outputs between real and synthetic images does not guarantee that a system relies on the same visual evidence.All the Facts, Still the Wrong Answer: Integration Gaps in Vision-Language Models
Multimodal reasoning requires models to combine multiple pieces of evidence into decisions that satisfy all relevant constraints.StateWise: Teaching Language Models to Track and Obey Evolving Constraints in Multi-Turn Dialogue
Users of conversational assistants rarely state all requirements up front: they add constraints, amend them, withdraw them, digress, and return.Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection
Zero-shot detection of machine-generated text is vital for mitigating the risks of large language models (LLMs) misuse.CFL-aware edge design for graph neural solvers of hyperbolic transport
Hyperbolic partial differential equations (PDEs) transport information at finite speed along characteristics, often producing shocks and discontinuities that are challenging to capture numerically.An actively trained neural operator for near-explicit atmospheric chemistry
Earth-system models simplify atmospheric chemistry into condensed mechanisms, because near-explicit mechanisms such as the Master Chemical Mechanism (MCM) are too costly to solve in every grid cell.The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS
Large Language Models excel at reasoning and generation but their autoregressive, token-by-token inference makes them unnecessarily slow, expensive, and poorly calibrated for the many routine…TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains
Retrieval-augmented generation (RAG) lets large language models (LLMs) answer knowledge-intensive questions from retrieved evidence, but adapting a general-purpose RAG system to a specialized domain…InfiniteWorld: Separating Visual Evidence from Familiar Physics
Physical reasoning requires adapting familiar expectations to the dynamics of the observed world.