{"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/lota-bench-benchmarking-language-oriented","title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","arxiv_id":"2402.08178","date":"2024-02-13","proceeding":null,"authors":["Jae-Woo Choi","Youngwoo Yoon","Hyobin Ong","Jaehong Kim","Minsu Jang"],"abstract":"Large language models (LLMs) have recently received considerable attention as alternative solutions for task planning. However, comparing the performance of language-oriented task planners becomes difficult, and there exists a dearth of detailed exploration regarding the effects of various factors such as pre-trained model selection and prompt construction. To address this, we propose a benchmark system for automatically quantifying performance of task planning for home-service embodied agents. Task planners are tested on two pairs of datasets and simulators: 1) ALFRED and AI2-THOR, 2) an extension of Watch-And-Help and VirtualHome. Using the proposed benchmark system, we perform extensive experiments with LLMs and prompts, and explore several enhancements of the baseline planner. We expect that the proposed benchmark tool would accelerate the development of language-oriented task planners.","url_abs":"https://arxiv.org/abs/2402.08178v1","url_pdf":"https://arxiv.org/pdf/2402.08178v1.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":"lota-bench-benchmarking-language-oriented","repo_url":"https://github.com/lbaa2022/llmtaskplanning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"task-planning","task_name":"Task Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.08178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08178"}},"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":"deterministic:regex_extraction","url":"https://github.com/lbaa2022/LLMTaskPlanning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lbaa2022/llmtaskplanning","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":10,"samples":[{"code_sha256_prefix":"2857a0217638cdb0","entry":"convert_low_level_action_to_nl_skill","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/examine_alfred_data.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/alfred/examine_alfred_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2857a0217638cdb0"}},{"code_sha256_prefix":"24a244e2bf4651ad","entry":"get_json_data","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/alfred_result_stat.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/alfred/alfred_result_stat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24a244e2bf4651ad"}},{"code_sha256_prefix":"d076bf1f3a9eae92","entry":"get_json_files","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/alfred_result_stat.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/alfred/alfred_result_stat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d076bf1f3a9eae92"}},{"code_sha256_prefix":"1cf7812afecd6dea","entry":"load_tasks","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/examine_alfred_data.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/alfred/examine_alfred_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1cf7812afecd6dea"}},{"code_sha256_prefix":"0c32c89b89a4cb67","entry":"separate_new_ids_graph","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/wah/wah_utils.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/wah/wah_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c32c89b89a4cb67"}},{"code_sha256_prefix":"87d889b4372c0014","entry":"split_step_sim","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/wah/wah_utils.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/wah/wah_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87d889b4372c0014"}},{"code_sha256_prefix":"642fa1c54ddca6da","entry":"step_nl2sim","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/wah/wah_utils.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/wah/wah_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"642fa1c54ddca6da"}},{"code_sha256_prefix":"8a0d0cc725d71a48","entry":"ithor_name_to_natural_word","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/utils.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/alfred/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a0d0cc725d71a48"}},{"code_sha256_prefix":"ce6ed1f3b29ee489","entry":"load_task_json","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/utils.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/src/alfred/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce6ed1f3b29ee489"}},{"code_sha256_prefix":"29f18b39e3b62010","entry":"print_gpu_usage","repo":"lbaa2022/LLMTaskPlanning","repo_kind":"official","path":"src/alfred/utils.py","file_url":"https://github.com/lbaa2022/LLMTaskPlanning/blob/HEAD/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29f18b39e3b62010"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}