arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.09252cs.CLcs.AIcs.HC
收藏

DAVIS:基于知识图谱的规划代理

DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue

Davis Institute for Artificial Intelligence(戴维斯人工智能研究所);Colby College(科伯学院);University of Notre Dame(圣约翰大学);William & Mary(威廉与玛丽学院)

Minh Pham Dinh, Munira Syed, Michael G Yankoski, Trenton W. Ford

AI总结:

本文提出DAVIS,一种基于知识图谱的规划代理,通过结构化和时间记忆实现模型驱动规划,并采用多轮检索系统提升科学任务处理能力,在ScienceWorld基准测试中表现优异。

摘要:

设计一个能够执行实验室任务的通用科学代理,以协助研究人员已成为人工智能研究的关键目标。与日常任务不同,科学任务更复杂且要求高,需要代理具备更高推理能力、对环境的结构和时间理解以及安全性的强强调。现有方法难以满足这些多方面需求。为解决这些问题,我们提出了DAVIS。不同于传统检索增强生成(RAG)方法,DAVIS整合了结构化和时间记忆,实现了基于模型的规划。此外,DAVIS实现了代理式的多轮检索系统,类似于人类的内心独白,允许在过去的经历上进行更深入的推理。DAVIS在ScienceWorld基准测试中,在8个基本科学科目上优于先前方法。此外,DAVIS的世界模型在著名的HotpotQA和MusiqueQA数据集上表现具有竞争力。据我们所知,DAVIS是首个在RAG流程中采用交互式检索方法的RAG代理。

英文摘要:

Designing a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers has become a key goal in recent Artificial Intelligence (AI) research. Unlike everyday tasks, scientific tasks are inherently more delicate and complex, requiring agents to possess a higher level of reasoning ability, structured and temporal understanding of their environment, and a strong emphasis on safety. Existing approaches often fail to address these multifaceted requirements. To tackle these challenges, we present DAVIS. Unlike traditional retrieval-augmented generation (RAG) approaches, DAVIS incorporates structured and temporal memory, which enables model-based planning. Additionally, DAVIS implements an agentic, multi-turn retrieval system, similar to a human's inner monologue, allowing for a greater degree of reasoning over past experiences. DAVIS demonstrates substantially improved performance on the ScienceWorld benchmark comparing to previous approaches on 8 out of 9 elementary science subjects. In addition, DAVIS's World Model demonstrates competitive performance on the famous HotpotQA and MusiqueQA dataset for multi-hop question answering. To the best of our knowledge, DAVIS is the first RAG agent to employ an interactive retrieval method in a RAG pipeline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑