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 232
Taming Softmax at the Limits of Muon: A Unified Approach through Hilbert Geometry
Muon controls weight updates through the RMS movement of a linear layer's output.Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models
Diffusion language models (DLMs) have attracted wide attention for their fast, parallel decoding, but they are believed to be far less efficient to train than autoregressive language models (ARMs)…Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites
Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly understood, particularly in underrepresented…Morphology-aware deep learning predicts colorectal cancer survival from whole-slide images
Five-year survival prediction from hematoxylin-and-eosin whole-slide images could support risk stratification, but the task is weakly supervised, and the tissue morphologies carrying prognostic…Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks
Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how it handles later tasks.OpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation
Recently, the integration of generative priors has revolutionized Monocular Depth Estimation (MDE), achieving state-of-the-art (SOTA) performance with remarkably high data efficiency.MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification
Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordinating complementary capabilities.RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning
Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the rubric carries and gives no GRPO reward gradient…4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling
For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated generation at different times and viewpoints.Executable Prefix Values for Locating Agent Failures
Work on debugging LLM agents treats the "first mistake" marked by a human or LLM judge as ground truth for where a trajectory failed.The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision
The Safety-Aware Denoiser (SAD) is a recent, training-free, safety-guidance framework for text diffusion models.Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)
Bias scores in language-model evaluations often conflate what a model prefers with whether it answers at all.When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?
An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmation, call one or several tools, escalate, or…Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents
Large language model (LLM) agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution.RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
Can vision-language models turn 2D observations into 3D understanding that supports precise action?DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps.PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning
Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require the probability of each action.Cowork-Gym: Synthesizing Interactive Work Environments at Scale
Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces.Encounter-Driven City-Scale Human Mobility Generation with Large Language Models
Large language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility preferences.Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning
Chain-of-thought (CoT) improves reasoning but incurs substantial autoregressive rationale cost.