Analyzing Information Sharing and Coordination in Multi-Agent Planning

2025-08-18

AI Summary

Multi-agent systems (MASs) face significant challenges in collaborative decision-making for long-horizon, multi-constraint planning tasks due to insufficient information sharing and inefficient coordination. Method: This paper proposes a structured LLM-based multi-agent framework addressing these limitations. Its core components include: (1) a structured notebook mechanism to mitigate LLM hallucinations and ensure cross-agent information consistency; and (2) a dedicated coordination agent that dynamically orchestrates subtask decomposition, dialogue flow, and reflective regulation. Results: Evaluated on the TravelPlanner benchmark, the framework achieves a 25% task success rate—representing a 17.5-percentage-point improvement over the single-agent baseline—while substantially reducing error rates. These results empirically validate the effectiveness of structured, LLM-driven collaboration for complex, dependency-rich planning tasks.

Technology Category

• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Multi-agent systems (MASs) have pushed the boundaries of large language model (LLM) agents in domains such as web research and software engineering. However, long-horizon, multi-constraint planning tasks involve conditioning on detailed information and satisfying complex interdependent constraints, which can pose a challenge for these systems. In this study, we construct an LLM-based MAS for a travel planning task which is representative of these challenges. We evaluate the impact of a notebook to facilitate information sharing, and evaluate an orchestrator agent to improve coordination in free form conversation between agents. We find that the notebook reduces errors due to hallucinated details by 18%, while an orchestrator directs the MAS to focus on and further reduce errors by up to 13.5% within focused sub-areas. Combining both mechanisms achieves a 25% final pass rate on the TravelPlanner benchmark, a 17.5% absolute improvement over the single-agent baseline's 7.5% pass rate. These results highlight the potential of structured information sharing and reflective orchestration as key components in MASs for long horizon planning with LLMs.

Problem

• Enhancing multi-agent coordination in complex planning tasks
• Reducing errors from hallucinated details in LLM agents
• Improving information sharing for long-horizon constraint satisfaction

Innovation

• LLM-based multi-agent system for travel planning
• Notebook reduces hallucinated details by 18%
• Orchestrator agent improves coordination by 13.5%