適應性領域建模與語言模型：多智能體任務規劃方法

摘要

我們介紹了TAPAS（基於任務的適應與規劃多代理框架），這是一個將大型語言模型（LLMs）與符號規劃相結合的多代理系統，旨在無需手動定義環境模型的情況下解決複雜任務。TAPAS利用專門的基於LLM的代理，通過結構化的工具調用機制協作生成並適應領域模型、初始狀態及目標規格。這種基於工具的交互方式使得下游代理能夠向上游代理請求修改，從而適應新的屬性和約束，而無需手動重新定義領域。結合自然語言計劃翻譯的ReAct（推理+行動）風格執行代理，彌合了動態生成計劃與現實世界機器人能力之間的差距。TAPAS在基準規劃領域及VirtualHome模擬現實環境中展現了卓越的性能。

English

We introduce TAPAS (Task-based Adaptation and Planning using AgentS), a multi-agent framework that integrates Large Language Models (LLMs) with symbolic planning to solve complex tasks without the need for manually defined environment models. TAPAS employs specialized LLM-based agents that collaboratively generate and adapt domain models, initial states, and goal specifications as needed using structured tool-calling mechanisms. Through this tool-based interaction, downstream agents can request modifications from upstream agents, enabling adaptation to novel attributes and constraints without manual domain redefinition. A ReAct (Reason+Act)-style execution agent, coupled with natural language plan translation, bridges the gap between dynamically generated plans and real-world robot capabilities. TAPAS demonstrates strong performance in benchmark planning domains and in the VirtualHome simulated real-world environment.

適應性領域建模與語言模型：多智能體任務規劃方法

Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning

摘要

Support