Lune

ICLR2025Top-tier venue

CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees G. M. Snoek, Jan-Jakob Sonke, Efstratios Gavves

Abstract

In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term strategic and cooperative planning, leading to redundant steps, failures, and even serious repercussions in complex tasks like search-and-rescue missions where discussion and cooperative plan are crucial. To solve this issue, we propose Cooperative Plan Optimization (CaPo) to enhance the cooperation efficiency of LLM-based embodied agents. Inspired by human cooperation schemes, CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and execution. In the first phase, all agents analyze the task, discuss, and cooperatively create a meta-plan that decomposes the task into subtasks with detailed steps, ensuring a long-term strategic and coherent plan for efficient coordination. In the second phase, agents execute tasks according to the meta-plan and dynamically adjust it based on their latest progress (e.g., discovering a target object) through multi-turn discussions. This progressbased adaptation eliminates redundant actions, improving the overall cooperation efficiency of agents. Experimental results on the ThreeDworld Multi-Agent Transport and Communicative Watch-And-Help tasks demonstrate CaPo's much higher task completion rate and efficiency compared with state-of-the-arts. The code is released at https://github.com/jliu4ai/CaPo.

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.

6 top-tier papers have 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

  • RoboAgent: Chaining Basic Capabilities for Embodied Task Planning cites Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
  • RoboAgent: Chaining Basic Capabilities for Embodied Task Planning cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • RoboAgent: Chaining Basic Capabilities for Embodied Task Planning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Self-Refine: Iterative Refinement with Self-Feedback cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Large Language Models are Zero-Shot Reasoners
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents cites Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
  • From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents 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 papers6

  1. Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM SystemsShangbin Feng, Zifeng Wang, Palash Goyal, Yike Wang et al.NeurIPS 2025 · 26 citations
  2. RoboAgent: Chaining Basic Capabilities for Embodied Task PlanningPeiran Xu, Jiaqi Zheng, Yadong MuCVPR 2026 · 6 citations
  3. From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied AgentsSeungwon Seo, Soobin Lim, SeongRae Noh, Haneul Kim et al.ICLR 2026 · 2 citations
  4. Great Minds Think Alike: Contextual Tacit Communication for Decentralized LLM-Agent CooperationYue Pei, Hongming Zhang, Jiarui Guan, Jusheng Zhang et al.ICML 2026
  5. Communication-Efficient Desire Alignment for Proactive Embodied Human-Agent InteractionYuanfei Wang, Xinju Huang, Fangwei Zhong, Yaodong Yang et al.ACL 2026

Builds on24

  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. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  3. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
  4. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging FaceYongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li et al.NeurIPS 2023 · 1,778 citations
  5. Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied AgentsWenlong Huang, Pieter Abbeel, Deepak Pathak, Igor MordatchICML 2022 · 1,539 citations

Related papers

  1. Collaborative Tree Search for Enhancing Embodied Multi-Agent CollaborationLizheng Zu, Lin Lin, Song Fu, Na Zhao et al.CVPR 2025
  2. MPO: Boosting LLM Agents with Meta Plan OptimizationWeimin Xiong, Yifan Song, Qingxiu Dong, Bingchan Zhao et al.EMNLP Findings 2025 · 2 citations
  3. CoPE: A Framework for Optimizing Coordination between Planning and Execution in LLM-based AgentsHuanxi Liu, Kun Hu, Qiang Wang, Yuanzhao Zhai et al.ICML 2026
  4. ReCA: Integrated Acceleration for Real-Time and Efficient Cooperative Embodied Autonomous AgentsZishen Wan, Yuhang Du, Mohamed Ibrahim, Jiayi Qian et al.ASPLOS 2025 · 7 citations
  5. LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent BehaviorQinhong Zhou, Chuang Gan, Anoop CherianICML 2026
Dusk over the sea between two cliffs drawn in fine vertical lines