mlsanityData to 7 Oct 2026

End-to-end PDDL Planning with Hardcoded and Dynamic Agents

arXiv 2512.09629 ↗First posted 10 Dec 2025cs.AI cs.LGcited by 5

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language and converts it into a PDDL (Planning Domain Definition Language) model, where the domain and problem are iteratively refined by sub-modules (agents) to address common planning requirements, such as time constraints and optimality, as well as ambiguities and contradictions that may exist in the human specification. We support two categories of agents: hardcoded, which are informed by logs and error traces and have a pre-defined goal (e.g., fix issues with PDDL syntax, check temporal constraints), and dynamic, which have no predefined goal but adapt to the specific domain and revise the latent planning abstraction. The validated domain and problem are then passed to an external planning engine to generate a plan. The orchestrator and agents are powered by Large Language Models (LLMs) and require no human intervention at any stage of the process. Finally, a module translates the final plan back into natural language to improve human readability while maintaining the correctness of each step. We demonstrate the flexibility and effectiveness of our framework on GPT-4o, 5-mini, 5.4, and Gemini-2.5, 3-flash across more than ten domains and tasks, including the Google NaturalPlan benchmark, Planbench, and classic planning problems like Sokoban, Blocksworld and the Tower of Hanoi, where LLMs are known to struggle even with small instances. Our framework can be integrated with any PDDL planning engine and validator (we successfully tested Fast Downward, LPG, POPF, VAL, and uVAL) and represents a significant step toward end-to-end planning aided by LLMs.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 25 of its 39 references that are in the map. First posted on arXiv 10 Dec 2025.

Builds on

25 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks12 Mar

Other references · 24

  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  3. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  4. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  5. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  6. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  7. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 429
  8. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  9. 2016Learning Multiagent Communication with Backpropagationcited by 355
  10. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 298
  11. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  12. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
12 more
  1. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
  2. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 107
  3. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 97
  4. 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchcited by 65
  5. 2023SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledgecited by 49
  6. 2024Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languagescited by 32
  7. 2024StructuredRAG: JSON Response Formatting with Large Language Modelscited by 22
  8. 2025Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 22
  9. 2024Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Modelscited by 17
  10. 2024Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks Worldcited by 9
  11. 2024Robust Planning with Compound LLM Architectures: An LLM-Modulo Approachcited by 8
  12. 2025A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraintscited by 6
  2. 2026SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Modelscited by 2
  3. 2026Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisationcited by 1
  4. 2026Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agentscited by 0
  5. 2026Neurosymbolic Embodied Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
  2. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
  3. 2025An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs
  4. 2025Toward PDDL Planning Copilot
  5. 2025Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
  6. 2026Language Models as Higher-Order Planning Formalizers
  7. 2024TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models
  8. 2025Generating Symbolic World Models via Test-time Scaling of Large Language Models