用世界模型提升LLM Agent在复杂任务中的规划与执行能力
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
- 引入生成式世界模型，让Agent在执行前模拟环境状态变化
- 在20多个MCP-Bench任务中，工具成功率与参数精度显著提升
- 支持自定义世界模型，适合需要长程规划的智能体研究者
模型上下文协议（MCP）统一了大语言模型与外部工具的接口，但智能体对运行环境的认知仍存在根本性缺失。现有范式分裂为：任务级规划忽略执行时动态，而反应式执行缺乏长远预见。本文提出MCP-Cosmos框架，将生成式世界模型（WM）融入MCP生态，实现预测性任务自动化。通过整合MCP、世界模型与智能体三类技术，我们验证了‘自带世界模型’（BYOWM）策略的有效性，使智能体能在潜在空间中模拟状态转移并优化计划。在20+个MCP-Bench任务上，采用ReAct与SPIRAL两种策略，结合2种规划模型和3种代表性世界模型进行实验，结果显示智能体环境交互关键指标如工具成功率与参数准确率均有提升。该框架还引入新度量标准‘执行质量’，可深入评估世界模型相对于基线的表现。
原文摘要 · Abstract (English)
The Model Context Protocol (MCP) has unified the interface between Large Language Models (LLMs) and external tools, yet a fundamental gap remains in how agents conceptualize the environments within which they operate. Current paradigms are bifurcated: Task-level planning often ignores execution-time dynamics, while reactive execution lacks long-horizon foresight. We present MCP-Cosmos, a framework that infuses generative World Models (WM) into the MCP ecosystem to enable predictive task automation. By unifying three disparate technologies, namely MCP, World Model, and Agent, we demonstrate that a "Bring Your Own World Model" (BYOWM) strategy allows agents to simulate state transitions and refine plans in a latent space before execution. We conducted experiments using two strategies, namely ReAct and SPIRAL with 2 planning models and 3 representative world models over 20+ MCP-Bench tasks. We observed improvements in Agent's environment interaction KPI such as tool success rate and tool parameter accuracy. The framework also offers new metrics such as Execution Quality to generate new insights about the effectiveness of world models compared to baseline.
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。