Autonomous Agents for Collaborative Task under Information Asymmetry

TL;DR

This paper introduces iAgents, a novel multi-agent system that overcomes information asymmetry by enabling proactive information exchange among agents, significantly improving collaborative task-solving in social networks.

Contribution

The paper proposes iAgents with a new reasoning mechanism, InfoNav, and a benchmark InformativeBench for evaluating LLM agents under information asymmetry conditions.

Findings

iAgents successfully collaborated within a network of 140 individuals and 588 relationships.

The system autonomously communicated over 30 turns and retrieved nearly 70,000 messages.

Tasks were completed within 3 minutes, demonstrating efficiency and effectiveness.

Abstract

Large Language Model Multi-Agent Systems (LLM-MAS) have achieved great progress in solving complex tasks. It performs communication among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents' collaborations are leveraged to perform multi-person tasks, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents' communication toward effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents' task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes.