REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents using Information Relevance and Relative Proximity

TL;DR

REVECA is a novel cognitive architecture for cooperative language agents that enhances planning, memory management, and validation to improve multi-agent collaboration under complex partial observations.

Contribution

The paper introduces REVECA, a new architecture utilizing relevance estimation and trajectory validation to address challenges in multi-agent cooperation with decentralized agents.

Findings

REVECA outperforms existing methods on various benchmarks.

It enables efficient memory management and optimal planning.

User study shows increased trustworthiness in human-AI cooperation.

Abstract

We address the challenge of multi-agent cooperation, where agents achieve a common goal by cooperating with decentralized agents under complex partial observations. Existing cooperative agent systems often struggle with efficiently processing continuously accumulating information, managing globally suboptimal planning due to lack of consideration of collaborators, and addressing false planning caused by environmental changes introduced by other collaborators. To overcome these challenges, we propose the RElevance, Proximity, and Validation-Enhanced Cooperative Language Agent (REVECA), a novel cognitive architecture powered by GPT-4o-mini. REVECA enables efficient memory management, optimal planning, and cost-effective prevention of false planning by leveraging Relevance Estimation, Adaptive Planning, and Trajectory-based Validation. Extensive experimental results demonstrate REVECA's superiority over existing methods across various benchmarks, while a user study reveals its potential for achieving trustworthy human-AI cooperation.