# Coding Agents for Generalized Task and Motion Planning Problems arXiv: https://arxiv.org/abs/2609.30233 ยท HTML: https://mlsanity.com/paper/2609.30233/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. - Builds on 25 of its 36 references that are in the map. - First posted on arXiv 24 Sep 2026. ## Placed in - LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/) ## Builds on (most cited first, 25 of 25) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024) - [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023) - [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022) - [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020) - [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020) - [Text2Motion: From Natural Language Instructions to Feasible Plans](https://mlsanity.com/paper/2303.12153/) (2023) - [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018) - [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023) - [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026) - [LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning](https://mlsanity.com/paper/2403.11552/) (2024) - [ASPIRE: Agentic /Skills Discovery for Robotics](https://mlsanity.com/paper/2607.00272/) (2026) - [Learning compositional models of robot skills for task and motion planning](https://mlsanity.com/paper/2006.06444/) (2020) - [RHO: Your Coding Agent is Secretly a Roboticist](https://mlsanity.com/paper/2606.16458/) (2026) - [Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction](https://mlsanity.com/paper/2406.05572/) (2024) - [Discovering State and Action Abstractions for Generalized Task and Motion Planning](https://mlsanity.com/paper/2109.11082/) (2021) - [Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code](https://mlsanity.com/paper/2503.18809/) (2025) - [GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Tasks](https://mlsanity.com/paper/2404.06645/) (2024) - [Open-World Task and Motion Planning via Vision-Language Model Generated Constraints](https://mlsanity.com/paper/2411.08253/) (2024) - [Demonstration-Free Robotic Control via LLM Agents](https://mlsanity.com/paper/2601.20334/) (2026) - [Frontier Large Language Models Rival State-of-the-Art Planners](https://mlsanity.com/paper/2511.09378/) (2025) - [A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream](https://mlsanity.com/paper/2510.00182/) (2025) - [Meta-Optimization and Program Search using Language Models for Task and Motion Planning](https://mlsanity.com/paper/2505.03725/) (2025) - [KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning](https://mlsanity.com/paper/2604.25788/) (2026) - [MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution](https://mlsanity.com/paper/2607.22832/) (2026) ## Built on by (most cited first, 2 of 2) - [EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning](https://mlsanity.com/paper/2609.35047/) (2026) - [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026) ## Abstract (arXiv) Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses this difficulty by exploiting regularities across problem instances to reduce planning effort on new instances. However, existing methods require substantial TAMP-specific engineering. We investigate whether coding agents can automate this process by synthesizing programs that generalize across instances. Given a task description and simulator access, each agent chooses how to interact with the environment while developing a program within a fixed synthesis budget. The program is then frozen and evaluated on unseen instances. We evaluate Claude Code (Opus 5) and Codex (GPT-5.6 Sol and GPT-6 Astra) on 28 simulated environments from KinDER and PDDLStream, with object counts beyond those evaluated in the original benchmark. Across all program synthesis methods, we evaluate 980 generated programs on 100 held-out instances each, 98,000 evaluation episodes in total. Overall, we find that coding agents are surprisingly effective at generalized TAMP: all three agent configurations outperform hand-engineered planners, one-shot generation, and an LLM-based generalized planning baseline in mean success (56% to 95% versus 47% for the planners, on the 16 environments where a planner is available). As object counts grow, the agents' programs maintain higher success than the planner, using an order of magnitude less computation per instance on average. Logs show agents using interaction to calibrate physical models, test edge cases, and refine strategies. We release all code, including the full prompts given to the agents. These findings suggest that coding agents are a strong baseline for generalized TAMP.