{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/embodied-cot-distillation-from-llm-to-off-the","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","arxiv_id":"2412.11499","date":"2024-12-16","proceeding":null,"authors":["Wonje Choi","Woo Kyung Kim","Minjong Yoo","Honguk Woo"],"abstract":"We address the challenge of utilizing large language models (LLMs) for complex embodied tasks, in the environment where decision-making systems operate timely on capacity-limited, off-the-shelf devices. We present DeDer, a framework for decomposing and distilling the embodied reasoning capabilities from LLMs to efficient, small language model (sLM)-based policies. In DeDer, the decision-making process of LLM-based strategies is restructured into a hierarchy with a reasoning-policy and planning-policy. The reasoning-policy is distilled from the data that is generated through the embodied in-context learning and self-verification of an LLM, so it can produce effective rationales. The planning-policy, guided by the rationales, can render optimized plans efficiently. In turn, DeDer allows for adopting sLMs for both policies, deployed on off-the-shelf devices. Furthermore, to enhance the quality of intermediate rationales, specific to embodied tasks, we devise the embodied knowledge graph, and to generate multiple rationales timely through a single inference, we also use the contrastively prompted attention model. Our experiments with the ALFRED benchmark demonstrate that DeDer surpasses leading language planning and distillation approaches, indicating the applicability and efficiency of sLM-based embodied policies derived through DeDer.","url_abs":"https://arxiv.org/abs/2412.11499v1","url_pdf":"https://arxiv.org/pdf/2412.11499v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"embodied-cot-distillation-from-llm-to-off-the","repo_url":"https://github.com/osu-nlp-group/llm-planner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"small-language-model","task_name":"Small Language Model"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.11499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11499"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osu-nlp-group/llm-planner","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"12ba53fedf724ead","entry":"get_action","repo":"osu-nlp-group/llm-planner","repo_kind":"official","path":"e2e/alfred/env/reward.py","file_url":"https://github.com/osu-nlp-group/llm-planner/blob/HEAD/e2e/alfred/env/reward.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12ba53fedf724ead"}},{"code_sha256_prefix":"5ffac7b83a094577","entry":"get_task","repo":"osu-nlp-group/llm-planner","repo_kind":"official","path":"e2e/alfred/env/tasks.py","file_url":"https://github.com/osu-nlp-group/llm-planner/blob/HEAD/e2e/alfred/env/tasks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ffac7b83a094577"}},{"code_sha256_prefix":"8a0d0cc725d71a48","entry":"ithor_name_to_natural_word","repo":"osu-nlp-group/llm-planner","repo_kind":"official","path":"e2e/src/alfred/utils.py","file_url":"https://github.com/osu-nlp-group/llm-planner/blob/HEAD/e2e/src/alfred/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a0d0cc725d71a48"}},{"code_sha256_prefix":"ce6ed1f3b29ee489","entry":"load_task_json","repo":"osu-nlp-group/llm-planner","repo_kind":"official","path":"e2e/src/alfred/utils.py","file_url":"https://github.com/osu-nlp-group/llm-planner/blob/HEAD/e2e/src/alfred/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce6ed1f3b29ee489"}},{"code_sha256_prefix":"d669c8373c54c13d","entry":"natural_word_to_ithor_name","repo":"osu-nlp-group/llm-planner","repo_kind":"official","path":"e2e/src/alfred/utils.py","file_url":"https://github.com/osu-nlp-group/llm-planner/blob/HEAD/e2e/src/alfred/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d669c8373c54c13d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}