# Toward PDDL Planning Copilot

arXiv: https://arxiv.org/abs/2509.12987 · HTML: https://mlsanity.com/paper/2509.12987/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [Can Large Language Models Reason and Plan?](https://mlsanity.com/paper/2403.04121/) (2024)
- [Understanding the Capabilities of Large Language Models for Automated Planning](https://mlsanity.com/paper/2305.16151/) (2023)
- [Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling](https://mlsanity.com/paper/2508.02979/) (2025)
- [Real-World Planning with PDDL+ and Beyond](https://mlsanity.com/paper/2402.11901/) (2024)
- [GenPlanX. Generation of Plans and Execution](https://mlsanity.com/paper/2506.10897/) (2025)
- [SLDB: An End-To-End Heterogeneous System-on-Chip Benchmark Suite for LLM-Aided Design](https://mlsanity.com/paper/2507.06376/) (2025)

## Built on by (most cited first, 1 of 1)

- [RAMP: Hybrid DRL for Online Learning of Numeric Action Models](https://mlsanity.com/paper/2604.08685/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly being used as autonomous agents capable of performing complicated tasks. However, they lack the ability to perform reliable long-horizon planning on their own. This paper bridges this gap by introducing the Planning Copilot, a chatbot that integrates multiple planning tools and allows users to invoke them through instructions in natural language. The Planning Copilot leverages the Model Context Protocol (MCP), a recently developed standard for connecting LLMs with external tools and systems. This approach allows using any LLM that supports MCP without domain-specific fine-tuning. Our Planning Copilot supports common planning tasks such as checking the syntax of planning problems, selecting an appropriate planner, calling it, validating the plan it generates, and simulating their execution. We empirically evaluate the ability of our Planning Copilot to perform these tasks using three open-source LLMs. The results show that the Planning Copilot highly outperforms using the same LLMs without the planning tools. We also conducted a limited qualitative comparison of our tool against Chat GPT-5, a very recent commercial LLM. Our results shows that our Planning Copilot significantly outperforms GPT-5 despite relying on a much smaller LLM. This suggests dedicated planning tools may be an effective way to enable LLMs to perform planning tasks.