# TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models

arXiv: https://arxiv.org/abs/2403.17246 · HTML: https://mlsanity.com/paper/2403.17246/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Placed in

- 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, 12 of 12)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2309.10062/) (2023)
- [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023)
- [Learning to Synthesize Programs as Interpretable and Generalizable Policies](https://mlsanity.com/paper/2108.13643/) (2021)
- [Task Planning in Robotics: an Empirical Comparison of PDDL-based and ASP-based Systems](https://mlsanity.com/paper/1804.08229/) (2018)
- [Solving Multiagent Planning Problems with Concurrent Conditional Effects](https://mlsanity.com/paper/1906.08157/) (2019)

## Built on by (most cited first, 29 of 29)

- [ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation](https://mlsanity.com/paper/2409.13682/) (2024)
- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [A Scalable Communication Protocol for Networks of Large Language Models](https://mlsanity.com/paper/2410.11905/) (2024)
- [Multi-agent Embodied AI: Advances and Future Directions](https://mlsanity.com/paper/2505.05108/) (2025)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner](https://mlsanity.com/paper/2409.20560/) (2024)
- [SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals](https://mlsanity.com/paper/2406.04784/) (2024)
- [DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning](https://mlsanity.com/paper/2406.09953/) (2024)
- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [Multi-Agent Systems for Robotic Autonomy with LLMs](https://mlsanity.com/paper/2505.05762/) (2025)
- [From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents](https://mlsanity.com/paper/2507.10644/) (2025)
- [CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments](https://mlsanity.com/paper/2503.00729/) (2025)
- [LLMPC: Large Language Model Predictive Control](https://mlsanity.com/paper/2501.02486/) (2025)
- [COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing Among Team of Autonomous LLM Agents](https://mlsanity.com/paper/2506.01900/) (2025)
- [ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration](https://mlsanity.com/paper/2509.24230/) (2025)
- [Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models](https://mlsanity.com/paper/2501.00953/) (2025)
- [RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks](https://mlsanity.com/paper/2506.06683/) (2025)
- [Learning Efficient Guardrails for Compliance](https://mlsanity.com/paper/2510.03485/) (2025)
- [PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language](https://mlsanity.com/paper/2510.22784/) (2025)
- [EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration](https://mlsanity.com/paper/2601.11063/) (2026)
- [KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning](https://mlsanity.com/paper/2602.04129/) (2026)
- [CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation](https://mlsanity.com/paper/2603.16215/) (2026)
- [Evaluating Creativity and Deception in Large Language Models: A Simulation Framework for Multi-Agent Balderdash](https://mlsanity.com/paper/2411.10422/) (2024)
- [HiBerNAC: Hierarchical Brain-inspired Robotic Neural Agent Collective for Disentangling Complex Manipulation](https://mlsanity.com/paper/2506.08296/) (2025)
- [TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks](https://mlsanity.com/paper/2604.06765/) (2026)
- [Mosaic: Runtime-Efficient Multi-Agent Embodied Planning](https://mlsanity.com/paper/2607.09603/) (2026)
- [RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning](https://mlsanity.com/paper/2510.10379/) (2025)
- [Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents](https://mlsanity.com/paper/2604.27699/) (2026)
- [One-to-Two Acting: A Novel Framework for Single-arm Agent Action Expansion to Dual Arms](https://mlsanity.com/paper/2606.19897/) (2026)

## Abstract (arXiv)

Classical planning formulations like the Planning Domain Definition Language (PDDL) admit action sequences guaranteed to achieve a goal state given an initial state if any are possible. However, reasoning problems defined in PDDL do not capture temporal aspects of action taking, such as concurrent actions between two agents when there are no conflicting conditions, without significant modification and definition to existing PDDL domains. A human expert aware of such constraints can decompose a goal into subgoals, each reachable through single agent planning, to take advantage of simultaneous actions. In contrast to classical planning, large language models (LLMs) directly used for inferring plan steps rarely guarantee execution success, but are capable of leveraging commonsense reasoning to assemble action sequences. We combine the strengths of both classical planning and LLMs by approximating human intuitions for multi-agent planning goal decomposition. We demonstrate that LLM-based goal decomposition leads to faster planning times than solving multi-agent PDDL problems directly while simultaneously achieving fewer plan execution steps than a single agent plan alone, as well as most multiagent plans, while guaranteeing execution success. Additionally, we find that LLM-based approximations of subgoals result in similar multi-agent execution lengths to those specified by human experts. Website and resources at https://glamor-usc.github.io/twostep