# Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models arXiv: https://arxiv.org/abs/2407.12532 ยท HTML: https://mlsanity.com/paper/2407.12532/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 24 of its 59 references that are in the map. - First posted on arXiv 17 Jul 2024. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 24 of 24) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023) - [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023) - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023) - [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021) - [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022) - [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023) - [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023) - [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023) - [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023) - [SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning](https://mlsanity.com/paper/2308.00436/) (2023) - [ROMA: Multi-Agent Reinforcement Learning with Emergent Roles](https://mlsanity.com/paper/2003.08039/) (2020) - [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023) - [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023) - [Agent Lumos: Unified and Modular Training for Open-Source Language Agents](https://mlsanity.com/paper/2311.05657/) (2023) - [CodeScore: Evaluating Code Generation by Learning Code Execution](https://mlsanity.com/paper/2301.09043/) (2023) - [Language Instructed Reinforcement Learning for Human-AI Coordination](https://mlsanity.com/paper/2304.07297/) (2023) - [A Computational Framework for Behavioral Assessment of LLM Therapists](https://mlsanity.com/paper/2401.00820/) (2024) - [LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning](https://mlsanity.com/paper/2401.00125/) (2023) - [Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.04402/) (2021) - [A Review of Cooperation in Multi-agent Learning](https://mlsanity.com/paper/2312.05162/) (2023) - [Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective Intelligence](https://mlsanity.com/paper/2307.02757/) (2023) - [Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models](https://mlsanity.com/paper/2404.11502/) (2024) - [Subequivariant Reinforcement Learning Framework for Coordinated Motion Control](https://mlsanity.com/paper/2403.15100/) (2024) ## Built on by (most cited first, 10 of 10) - [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025) - [The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process](https://mlsanity.com/paper/2506.01080/) (2025) - [Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems](https://mlsanity.com/paper/2502.11098/) (2025) - [How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs](https://mlsanity.com/paper/2507.08960/) (2025) - [Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning](https://mlsanity.com/paper/2509.21193/) (2025) - [When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements](https://mlsanity.com/paper/2502.15153/) (2025) - [Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models](https://mlsanity.com/paper/2508.02912/) (2025) - [Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation](https://mlsanity.com/paper/2602.19304/) (2026) - [Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data](https://mlsanity.com/paper/2511.14098/) (2025) - [Modular Speaker Architecture: A Framework for Sustaining Responsibility and Contextual Integrity in Multi-Agent AI Communication](https://mlsanity.com/paper/2506.01095/) (2025) ## Abstract (arXiv) Effective collaboration in multi-agent systems requires communicating goals and intentions between agents. Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter-module communication, frequently leading to suboptimal multi-agent reinforcement learning (MARL) policies and inadequate task coordination. To address these challenges, we present a framework for training large language models (LLMs) as collaborative agents to enable coordinated behaviors in cooperative MARL. Each agent maintains a private intention consisting of its current goal and associated sub-tasks. Agents broadcast their intentions periodically, allowing other agents to infer coordination tasks. A propagation network transforms broadcast intentions into teammate-specific communication messages, sharing relevant goals with designated teammates. The architecture of our framework is structured into planning, grounding, and execution modules. During execution, multiple agents interact in a downstream environment and communicate intentions to enable coordinated behaviors. The grounding module dynamically adapts comprehension strategies based on emerging coordination patterns, while feedback from execution agents influnces the planning module, enabling the dynamic re-planning of sub-tasks. Results in collaborative environment simulation demonstrate intention propagation reduces miscoordination errors by aligning sub-task dependencies between agents. Agents learn when to communicate intentions and which teammates require task details, resulting in emergent coordinated behaviors. This demonstrates the efficacy of intention sharing for cooperative multi-agent RL based on LLMs.