让大模型智能体在新环境自动生成场景并优化动作策略
SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
- 用多步动作合成构建虚拟场景，支持智能体自主探索
- 结合蒙特卡洛树搜索，显著提升新环境下的动作学习效率
- 适合需要自主规划与适应的智能体系统研究者使用
在智能体与环境的交互中，智能体通过规划和执行动作来拓展能力。然而，基于大语言模型的智能体在面对新环境或非常规动作空间时面临重大挑战。为使智能体能够自主探索环境、优化工作流并深化对动作的理解，我们提出 SynWorld 框架，该框架允许智能体在动作空间内合成多步动作的可能场景，并通过蒙特卡洛树搜索（MCTS）进行探索，以有效完善当前环境中的动作知识。实验表明，SynWorld 是一种在新环境中学习动作知识的有效且通用的方法。代码已开源：https://github.com/zjunlp/SynWorld。
原文摘要 · Abstract (English)
In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments. Code is available at https://github.com/zjunlp/SynWorld.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。