# End-to-end PDDL Planning with Hardcoded and Dynamic Agents arXiv: https://arxiv.org/abs/2512.09629 ยท HTML: https://mlsanity.com/paper/2512.09629/ ## Key facts - Cited by 5 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 25 of its 39 references that are in the map. - First posted on arXiv 10 Dec 2025. ## 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, 25 of 25) - [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022) - [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017) - [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020) - [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019) - [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016) - [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023) - [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024) - [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022) - [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016) - [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) - [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025) - [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024) - [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023) - [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024) - [Can Large Language Models Really Improve by Self-critiquing Their Own Plans?](https://mlsanity.com/paper/2310.08118/) (2023) - [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021) - [AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench](https://mlsanity.com/paper/2507.02554/) (2025) - [SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge](https://mlsanity.com/paper/2308.12682/) (2023) - [Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages](https://mlsanity.com/paper/2407.03321/) (2024) - [Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.09250/) (2025) - [StructuredRAG: JSON Response Formatting with Large Language Models](https://mlsanity.com/paper/2408.11061/) (2024) - [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://mlsanity.com/paper/2407.12979/) (2024) - [Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World](https://mlsanity.com/paper/2404.00246/) (2024) - [Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach](https://mlsanity.com/paper/2411.14484/) (2024) - [A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems](https://mlsanity.com/paper/2505.13252/) (2025) ## Built on by (most cited first, 5 of 5) - [AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints](https://mlsanity.com/paper/2606.05622/) (2026) - [SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models](https://mlsanity.com/paper/2601.20856/) (2026) - [Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation](https://mlsanity.com/paper/2603.06064/) (2026) - [Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents](https://mlsanity.com/paper/2606.21740/) (2026) - [Neurosymbolic Embodied Agents](https://mlsanity.com/paper/2608.16794/) (2026) ## 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.