Make Planning Research Rigorous Again!
Not on the map. Why?
Abstract (arXiv)
In over sixty years since its inception, the field of planning has made significant contributions to both the theory and practice of building planning software that can solve a never-before-seen planning problem. This was done through established practices of rigorous design and evaluation of planning systems. It is our position that this rigor should be applied to the current trend of work on planning with large language models. One way to do so is by correctly incorporating the insights, tools, and data from the automated planning community into the design and evaluation of LLM-based planners. The experience and expertise of the planning community are not just important from a historical perspective; the lessons learned could play a crucial role in accelerating the development of LLM-based planners. This position is particularly important in light of the abundance of recent works that replicate and propagate the same pitfalls that the planning community has encountered and learned from. We believe that avoiding such known pitfalls will contribute greatly to the progress in building LLM-based planners and to planning in general.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 115 references that are in the map. First posted on arXiv 27 May 2025.
Builds on
28 of 115 references.
References · 28
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
- 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
- 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
- 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
- 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
- 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
- 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 339
- 2018TextWorld: A Learning Environment for Text-based Gamescited by 310
- 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
- 2024Stream of Search (SoS): Learning to Search in Languagecited by 145
16 more
- 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
- 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 128
- 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
- 2024Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrappingcited by 90
- 2024ACPBench: Reasoning about Action, Change, and Planningcited by 39
- 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
- 2024System-1.x: Learning to Balance Fast and Slow Planning with Language Modelscited by 35
- 2024Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languagescited by 33
- 2024Thought of Search: Planning with Language Models Through The Lens of Efficiencycited by 32
- 2023Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planningcited by 24
- 2024NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptionscited by 22
- 2014Compiling Uncertainty Away in Conformant Planning Problems with Bounded Widthcited by 11
- 2014Soft Goals Can Be Compiled Awaycited by 8
- 2023What Planning Problems Can A Relational Neural Network Solve?cited by 8
- 2024ActionReasoningBench: Reasoning about Actions with and without Ramification Constraintscited by 4
- 2014Implicit Abstraction Heuristicscited by 1
Built on by
Not cited yet.