# Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning

arXiv: https://arxiv.org/abs/2504.17950 · HTML: https://mlsanity.com/paper/2504.17950/

## Key facts

- Cited by 21 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 8 of its 32 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## 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 / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 8 of 8)

- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks](https://mlsanity.com/paper/2411.00081/) (2024)
- [MALT: Improving Reasoning with Multi-Agent LLM Training](https://mlsanity.com/paper/2412.01928/) (2024)
- [LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models](https://mlsanity.com/paper/2310.03903/) (2023)
- [Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.08115/) (2024)
- [Infer Human's Intentions Before Following Natural Language Instructions](https://mlsanity.com/paper/2409.18073/) (2024)
- [CPS-TaskForge: Generating Collaborative Problem Solving Environments for Diverse Communication Tasks](https://mlsanity.com/paper/2408.08853/) (2024)

## Built on by (most cited first, 21 of 21)

- [SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions](https://mlsanity.com/paper/2506.23046/) (2025)
- [SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds](https://mlsanity.com/paper/2512.01078/) (2025)
- [Evolving Programmatic Skill Networks](https://mlsanity.com/paper/2601.03509/) (2026)
- [TextAtari: 100K Frames Game Playing with Language Agents](https://mlsanity.com/paper/2506.04098/) (2025)
- [DeliveryBench: Can Agents Earn Profit in Real World?](https://mlsanity.com/paper/2512.19234/) (2025)
- [Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game](https://mlsanity.com/paper/2604.18975/) (2026)
- [MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments](https://mlsanity.com/paper/2606.31966/) (2026)
- [EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration](https://mlsanity.com/paper/2601.11063/) (2026)
- [Scaling Participation in Modular AI Systems](https://mlsanity.com/paper/2606.07812/) (2026)
- [GuessBench: Sensemaking Multimodal Creativity in the Wild](https://mlsanity.com/paper/2506.00814/) (2025)
- [Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values](https://mlsanity.com/paper/2506.13774/) (2025)
- [Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft](https://mlsanity.com/paper/2606.15684/) (2026)
- [Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup](https://mlsanity.com/paper/2512.06256/) (2025)
- [Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science](https://mlsanity.com/paper/2602.05289/) (2026)
- [Structured LLM Reasoning for Zero-Shot Human--Robot Coordination Under Hidden Goals](https://mlsanity.com/paper/2608.04309/) (2026)
- [Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities](https://mlsanity.com/paper/2608.08045/) (2026)
- [GenCoord: Executable Commitments for Embodied LLM Agents under Private Information](https://mlsanity.com/paper/2608.22055/) (2026)
- [Decoupling Planning and Control for Instructable Agents](https://mlsanity.com/paper/2608.26788/) (2026)
- [CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning](https://mlsanity.com/paper/2608.28266/) (2026)
- [MineCEraft: Evaluating Language Models as Construction Engineers in the World of Minecraft](https://mlsanity.com/paper/2608.28884/) (2026)
- [Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration](https://mlsanity.com/paper/2610.16895/) (2026)

## Abstract (arXiv)

Collaboration is ubiquitous and essential in day-to-day life -- from exchanging ideas, to delegating tasks, to generating plans together. This work studies how LLMs can adaptively collaborate to perform complex embodied reasoning tasks. To this end we introduce MINDcraft, an easily extensible platform built to enable LLM agents to control characters in the open-world game of Minecraft; and MineCollab, a benchmark to test the different dimensions of embodied and collaborative reasoning. An experimental study finds that the primary bottleneck in collaborating effectively for current state-of-the-art agents is efficient natural language communication, with agent performance dropping as much as 15% when they are required to communicate detailed task completion plans. We conclude that existing LLM agents are ill-optimized for multi-agent collaboration, especially in embodied scenarios, and highlight the need to employ methods beyond in-context and imitation learning. Our website can be found here: https://mindcraft-minecollab.github.io/