Lune

EMNLP Findings2025

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration

Chunhao Tian, Yutong Wang, Xuebo Liu, Zhexuan Wang, Liang Ding, Miao Zhang, Min Zhang

Abstract

Proper initialization is crucial for any system, particularly in multi-agent systems (MAS), where it plays a pivotal role in determining both the system's efficiency and effectiveness. However, existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages. Inspired by the principles of effective team composition, we propose AgentInit, which aims to optimize the structure of agent teams. Specifically, in addition to multi-round interactions and reflections between agents during agent generation, AgentInit incorporates a Natural Language to Format mechanism to ensure consistency and standardization. Balanced team selection strategies using Pareto principles are subsequently applied to jointly consider agent team diversity and task relevance to promote effective and efficient collaboration and enhance overall system performance. Experiments show that AgentInit consistently outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks, achieving an overall performance improvement of up to 1.2 and 1.6, respectively, while also significantly reducing token consumption. Further analysis confirms its strong transferability to similar tasks and verifies the effectiveness of its key components, demonstrating its capability and adaptability as a reliable MAS initialization method. Source code and models are available at https: //github.com/1737423697/AgentInit.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites Improving Factuality and Reasoning in Language Models through Multiagent Debate
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Improving Factuality and Reasoning in Language Models through Multiagent Debate cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. AgentVocab: Structure-Aware Vocabulary Adaptation for Efficient LLM AgentsKai Bian, Haosi Mo, Xuebo Liu, Shuangyong Song et al.ICML 2026

Builds on18

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained TransformersWenhui Wang, Furu Wei, Li Dong, Hangbo Bao et al.NeurIPS 2020 · 2,727 citations
  3. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
  4. Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
  5. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsWeize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang et al.ICLR 2024 · 594 citations

Related papers

  1. AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent CollaborationZhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding et al.ACL 2025 · 32 citations
  2. MAS-Architect: Declarative Multi-Agent System Design via Separation of ConcernsJing Huang, Lidong Zhang, Mutian Bao, Yadong Li et al.ICML 2026
  3. OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent CollaborationShijun Li, Hilaf Hasson, Joydeep GhoshICML 2026
  4. Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph GenerationShiyuan Li, Yixin Liu, Qingsong Wen, Chengqi Zhang et al.AAAI 2026 · 29 citations
  5. AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent SystemsYulang Chen, Haoxuan Peng, Jinyan Liu, Zichen Wen et al.ACL 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines