{"ID":2863197,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24160","arxiv_id":"2509.24160","title":"Memory Transfer Planning: LLM-driven Context-Aware Code Adaptation for Robot Manipulation","abstract":"Large language models (LLMs) are increasingly explored in robot manipulation, but many existing methods struggle to adapt to new environments. Many systems require either environment-specific policy training or depend on fixed prompts and single-shot code generation, leading to limited transferability and manual re-tuning. We introduce Memory Transfer Planning (MTP), a framework that leverages successful control-code examples from different environments as procedural knowledge, using them as in-context guidance for LLM-driven planning. Specifically, MTP (i) generates an initial plan and code using LLMs, (ii) retrieves relevant successful examples from a code memory, and (iii) contextually adapts the retrieved code to the target setting for re-planning without updating model parameters. We evaluate MTP on RLBench, CALVIN, and a physical robot, demonstrating effectiveness beyond simulation. Across these settings, MTP consistently improved success rate and adaptability compared with fixed-prompt code generation, naive retrieval, and memory-free re-planning. Furthermore, in hardware experiments, leveraging a memory constructed in simulation proved effective. MTP provides a practical approach that exploits procedural knowledge to realize robust LLM-based planning across diverse robotic manipulation scenarios, enhancing adaptability to novel environments and bridging simulation and real-world deployment.","short_abstract":"Large language models (LLMs) are increasingly explored in robot manipulation, but many existing methods struggle to adapt to new environments. Many systems require either environment-specific policy training or depend on fixed prompts and single-shot code generation, leading to limited transferability and manual re-tun...","url_abs":"https://arxiv.org/abs/2509.24160","url_pdf":"https://arxiv.org/pdf/2509.24160v1","authors":"[\"Tomoyuki Kagaya\",\"Subramanian Lakshmi\",\"Yuxuan Lou\",\"Thong Jing Yuan\",\"Jayashree Karlekar\",\"Sugiri Pranata\",\"Natsuki Murakami\",\"Akira Kinose\",\"Yang You\"]","published":"2025-09-29T01:18:59Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}