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 230
Replicable Dueling Bandits
Dueling bandits choose each comparison based on earlier noisy outcomes, so two runs on the same preferences can compare different pairs.Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models
Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts.A Multi-Tiered AI Accessibility Model (MAIAM): Proportionate Access and Capability Limits for Comprehensive Frontier AI Safety
Most debate about releasing capable AI systems treats the choice as binary: keep the model behind an API, or publish the weights.Defining and Generating Compositional Structure
Compositional structure is pervasive in nature and across scales: atoms combine into molecules, molecules into cells, and cells into organisms, while further compositional hierarchies appear within…SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills
Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience.RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks
Engineering agents must produce artifacts that satisfy exact, coupled constraints.MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high…Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming
We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors.LEV: Thinking Fast and Deep with Looped Decision Models
Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text.Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents
Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web.StepSafe: Learning Timely Intervention with Context-Aware Safety Reasoning
Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and interactions among agents.MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data
Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data.SOMA: Stack-of-Objects Manipulation using a Quadruped Robot
Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulators.How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts
Compiler transformations interact, making GPU kernel optimization a search for combinations that preserve the computation while improving performance.EigDiff: Eigensample Diffusion - or how to significantly reduce training dataset size with marginal performance variation?
Diffusion models are notoriously expensive to train, requiring large-scale datasets to learn how to gradually reverse the noise from images over multiple small denoising steps.Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation
Deep Reinforcement Learning (DRL) offers learned job selection for High-Performance Computing (HPC), but performance against heuristics alone does not establish value beyond action masking.CausalEvo: Causal Skill Self-Evolution for Health LLM Agents
Large language model (LLM) agents for health can accumulate reusable textual skills from task feedback, such as calculation criteria, measurement time points, and formula units.Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight
When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from exactly the problems it most needs to learn.Learning to Read Out: Unembedding Dynamics in Language Model Pretraining
When does a language model acquire a capability?Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation
Existing large language model (LLM)-based user encoders serialize heterogeneous behavioral logs and compress them into static representations through autoregressive (AR) prediction.