Papers

• Video-Based Reward Modeling for Computer-Use Agents

  Mohamed bin Zayed University of Artificial Intelligence, University of Southern California, University of Washington

  Published on: 2026-03-10 9 authors
• Interactive World Simulator for Robot Policy Training and Evaluation

  Columbia University, Toyota Research Institute, University of Illinois Urbana-Champaign

  Published on: 2026-03-09 10 authors
• SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans

  University of Illinois Urbana-Champaign, University of Massachusetts Amherst, University of Montreal, University of San Diego

  Published on: 2026-03-09 10 authors
• RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detection

  Hong Kong University of Science and Technology, Xi'an Jiaotong University

  Published on: 2026-03-08 6 authors
• ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

  Hong Kong University of Science and Technology, The Hong Kong University of Science and Technology (Guangzhou)

  Published on: 2026-03-06 6 authors
• The World Won't Stay Still: Programmable Evolution for Agent Benchmarks

  University of California

  Published on: 2026-03-06 14 authors
• DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality

  Boston University, Duke University

  Published on: 2026-03-06 6 authors
• SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement

  Northeastern University, Stanford University, University of Cambridge

  Published on: 2026-03-06 4 authors
• When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On

  Allen Institute for AI, University of Washington

  Published on: 2026-03-05 4 authors
• CodeScout: Contextual Problem Statement Enhancement for Software Agents

  University of Maryland

  Published on: 2026-03-05 8 authors
• STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks

  University of Massachusetts Amherst

  Published on: 2026-03-05 1 author
• SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning

  The Pennsylvania State University

  Published on: 2026-02-23 1 author
• Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching

  University of California

  Published on: 2026-02-17 1 author
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

  Boston University, Carnegie Mellon University, Columbia University, Dartmouth College, Duke University, Michigan State University, Princeton University, Stanford University, The Ohio State University, University of California, University of Oxford, University of Southern California, University of Texas

  Published on: 2026-02-13 1 author
• Visual Foresight for Robotic Stow: A Diffusion-Based World Model from Sparse Snapshots

  Published on: 2026-02-12 1 author
• Iterative Reranking as a Compute-Scaling Method for LLM-based Rankers

  Sapienza University

  Published on: 2026-02-12 1 author
• KG-CRAFT: Knowledge graph-based contrastive reasoning with LLMs for enhancing automated fact-checking

  Universidade Federal Fluminense

  Published on: 2026-02-12 1 author
• Pattern Discovery with Wide-Lens Analysis and Sharp-Focus Validation

  University of California

  Published on: 2026-02-12 1 author
• Autoregressive Image Generation with Masked Bit Modeling

  Published on: 2026-02-09 1 author
• AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

  Carnegie Mellon University

  Published on: 2026-02-03 1 author
• Interpretable Tabular Foundation Models via In-Context Kernel Regression

  Humboldt-Universität zu Berlin

  Published on: 2026-02-02 1 author
• RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation

  University of Washington

  Published on: 2026-02-02 1 author
• Differentiable Semantic ID for Generative Recommendation

  University of Glasgow

  Published on: 2026-01-27 1 author
• AnyView: Synthesizing Any Novel View in Dynamic Scenes

  Toyota Research Institute

  Published on: 2026-01-23 1 author
• MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

  University of California

  Published on: 2026-01-18 1 author
• TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback

  Georgia Institute of Technology

  Published on: 2026-01-13 1 author
• Internal Representations as Indicators of Hallucinations in Agent Tool Selection

  Published on: 2026-01-08 1 author
• ELLA: Efficient Lifelong Learning for Adapters

  Purdue University

  Published on: 2026-01-05 1 author
• Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

  The Chinese University of Hong Kong

  Published on: 2026-01-05 1 author
• Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking

  University of Wisconsin-Madison

  Published on: 2025-12-19 1 author
• Diffusion Language Model Inference with Monte Carlo Tree Search

  Dartmouth College

  Published on: 2025-12-13 1 author
• s3: You Don't Need That Much Data to Train a Search Agent via RL

  University of Illinois Urbana-Champaign

  Published on: 2025-11-05 1 author
• A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications

  The Pennsylvania State University

  Published on: 2025-10-27 1 author
• Chronos-2: From Univariate to Universal Forecasting

  University of Freiburg

  Published on: 2025-10-17 1 author
• WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

  University of Virginia

  Published on: 2025-10-08 1 author
• TabArena: A Living Benchmark for Machine Learning on Tabular Data

  University of Freiburg

  Published on: 2025-10-03 1 author
• Amazon Ads Multi-Touch Attribution

  Northwestern University

  Published on: 2025-08-11 1 author
• Establishing Best Practices for Building Rigorous Agentic Benchmarks

  Stanford University

  Published on: 2025-08-07 1 author
• Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

  Princeton University

  Published on: 2025-08-05 1 author
• MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning

  Massachusetts Institute of Technology

  Published on: 2025-07-12 1 author
• Evaluating the Critical Risks of Amazon’s Nova Premier under the Frontier Model Safety Framework

  Published on: 2025-07-07 1 author
• Steering Your Diffusion Policy with Latent Space Reinforcement Learning

  University of California, University of Washington

  Published on: 2025-06-25 1 author
• HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases

  Carnegie Mellon University

  Published on: 2025-06-02 1 author
• M+: Extending MemoryLLM with Scalable Long-Term Memory

  Massachusetts Institute of Technology, University of California

  Published on: 2025-05-30 1 author
• How Does Critical Batch Size Scale in Pre-training?

  Harvard University

  Published on: 2025-04-21 1 author
• A Systematic Survey of Automatic Prompt Optimization Techniques

  Published on: 2025-04-02 1 author
• The Amazon Nova Family of Models: Technical Report and Model Card

  Published on: 2025-03-17 1 author
• Evaluating Nova 2.0 Lite model under Amazon’s Frontier Model Safety Framework

  Published on: 2025-02-27 1 author
• Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

  Carnegie Mellon University, Harvard University

  Published on: 2025-02-25 1 author
• Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

  Massachusetts Institute of Technology, Northwestern University, Stanford University

  Published on: 2025-01-19 1 author