long-horizon reasoning

5 papers

• Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning
• Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
• Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
• ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
• WebThinker: Empowering Large Reasoning Models with Deep Research Capability