DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue

TL;DR

DAVIS is a novel scientific agent that uses structured memory and an inner monologue-like retrieval system to improve reasoning and performance across various science tasks and question-answering benchmarks.

Contribution

It introduces DAVIS, the first RAG agent with an interactive retrieval system and structured memory for enhanced reasoning in scientific tasks.

Findings

Outperforms previous methods on 8 out of 9 ScienceWorld subjects.

Shows competitive results on HotpotQA and MusiqueQA datasets.

First RAG agent to incorporate an interactive retrieval approach.

Abstract

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.