Paper Notes

标签: paper/agent/rl

此标签下有17条笔记。

  • 2026年5月

    Imperfect World Models are Exploitable

  • 2026年5月

    RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

  • 2026年5月

    SEAL: Synergistic Co-Evolution of Agents and Learning Environments

  • 2025年12月

    Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

  • 2025年9月

    Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs

  • 2025年9月

    Tree Search for LLM Agent Reinforcement Learning

  • 2025年7月

    Agentic Reinforced Policy Optimization

  • 2025年5月

    Absolute Zero: Reinforced Self-play Reasoning with Zero Data

  • 2025年5月

    Group-in-Group Policy Optimization for LLM Agent Training

  • 2025年4月

    Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning

  • 2025年4月

    ToolRL: Reward is All Tool Learning Needs

  • 2025年3月

    ToRL: Scaling Tool-Integrated RL

  • 2025年2月

    Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

  • 2025年2月

    SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

  • 2025年1月

    DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

  • 2023年5月

    Reasoning with Language Model is Planning with World Model

  • 2023年5月

    VOYAGER: An Open-Ended Embodied Agent with Large Language Models


Created with Quartz v4.5.2 © 2026

  • Source