Improved Generalized Planning with LLMs through Strategy Refinement and Reflection

• URL: http://arxiv.org/abs/2508.13876v1
• Date: Tue, 19 Aug 2025 14:42:18 GMT
• Title: Improved Generalized Planning with LLMs through Strategy Refinement and Reflection
• Authors: Katharina Stein, Nils Hodel, Daniel Fišer, Jörg Hoffmann, Michael Katz, Alexander Koller,
• Abstract summary: We introduce an approach that generates the strategy in the form of pseudocode.<n>We extend the Python debug phase with a reflection step prompting the LLM to pinpoint the reason for the observed plan failure.<n>Running experiments on 17 benchmark domains, we show that these extensions substantially improve the quality of the generalized plans.
• Score: 58.79806530685551
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs have recently been used to generate Python programs representing generalized plans in PDDL planning, i.e., plans that generalize across the tasks of a given PDDL domain. Previous work proposed a framework consisting of three steps: the LLM first generates a summary and then a strategy for the domain, both in natural language, and then implements that strategy as a Python program, that gets debugged on example planning tasks. In that work, only one strategy is generated and passed directly to the program generation. If the strategy is incorrect, its implementation will therefore result in an incorrect generalized plan. Here, we introduce an approach that generates the strategy in the form of pseudocode and enables automatic debugging of the pseudocode, hence allowing us to identify and fix errors prior to the generation of the generalized plan itself. Additionally, we extend the Python debugging phase with a reflection step prompting the LLM to pinpoint the reason for the observed plan failure. Finally, we take inspiration from LLM code generation to produce several program variants and pick the best one. Running experiments on 17 benchmark domains, we show that these extensions substantially improve (and never deteriorate) the quality of the generalized plans. In 12 of the domains, our best Python programs solve all tasks that can be generated with the respective instance generator.

Related papers

• Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code [8.971234046933349]
  Large language models (LLMs) fail to plan reliably, even when prompted with a detailed definition of a planning task.<n>We show how to use LLMs to generate correct plans, even for out-of-distribution tasks of increasing size.
  arXiv  Detail & Related papers  (2025-03-24T15:50:20Z)
• Query-Efficient Planning with Language Models [8.136901056728945]
  Planning in complex environments requires an agent to efficiently query a world model to find a sequence of actions from start to goal.<n>Recent work has shown that Large Language Models (LLMs) can potentially help with planning by searching over promising states and adapting to feedback from the world.<n>We show that while both approaches improve upon comparable baselines, using an LLM as a generative planner results in significantly fewer interactions.
  arXiv  Detail & Related papers  (2024-12-09T02:51:21Z)
• Interactive and Expressive Code-Augmented Planning with Large Language Models [62.799579304821826]
  Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. We propose REPL-Plan, an LLM planning approach that is fully code-expressive and dynamic.
  arXiv  Detail & Related papers  (2024-11-21T04:23:17Z)
• AdaPlanner: Adaptive Planning from Feedback with Language Models [56.367020818139665]
  Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities.
  arXiv  Detail & Related papers  (2023-05-26T05:52:27Z)
• Understanding the Capabilities of Large Language Models for Automated Planning [24.37599752610625]
  The study seeks to shed light on the capabilities of LLMs in solving complex planning problems. It provides insights into the most effective approaches for using LLMs in this context.
  arXiv  Detail & Related papers  (2023-05-25T15:21:09Z)
• Generalized Planning in PDDL Domains with Pretrained Large Language Models [82.24479434984426]
  We consider PDDL domains and use GPT-4 to synthesize Python programs. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines.
  arXiv  Detail & Related papers  (2023-05-18T14:48:20Z)
• Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents [99.17668730578586]
  Pre-trained large language models (LLMs) capture procedural knowledge about the world. Plan, Eliminate, and Track (PET) framework translates a task description into a list of high-level sub-tasks. PET framework leads to a significant 15% improvement over SOTA for generalization to human goal specifications.
  arXiv  Detail & Related papers  (2023-05-03T20:11:22Z)
• LLM+P: Empowering Large Language Models with Optimal Planning Proficiency [46.20085545432116]
  Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities. classical planners, once a problem is given in a formatted way, can use efficient search algorithms to quickly identify correct, or even optimal, plans. This paper introduces LLM+P, the first framework that incorporates the strengths of classical planners into LLMs.
  arXiv  Detail & Related papers  (2023-04-22T20:34:03Z)
• Learning to Plan with Natural Language [111.76828049344839]
  Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks. For completing the complex task, we still need a plan for the task to guide LLMs to generate the specific solutions step by step. We propose the Learning to Plan method, which involves two phases: (1) In the first learning task plan phase, it iteratively updates the task plan with new step-by-step solutions and behavioral instructions, which are obtained by prompting LLMs to derive from training error feedback.
  arXiv  Detail & Related papers  (2023-04-20T17:09:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.