{"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/epd-long-term-memory-extraction-context","title":"EPD: Long-term Memory Extraction, Context-awared Planning and Multi-iteration Decision @ EgoPlan Challenge ICML 2024","arxiv_id":"2407.19510","date":"2024-07-28","proceeding":null,"authors":["Letian Shi","Qi Lv","Xiang Deng","Liqiang Nie"],"abstract":"In this technical report, we present our solution for the EgoPlan Challenge in ICML 2024. To address the real-world egocentric task planning problem, we introduce a novel planning framework which comprises three stages: long-term memory Extraction, context-awared Planning, and multi-iteration Decision, named EPD. Given the task goal, task progress, and current observation, the extraction model first extracts task-relevant memory information from the progress video, transforming the complex long video into summarized memory information. The planning model then combines the context of the memory information with fine-grained visual information from the current observation to predict the next action. Finally, through multi-iteration decision-making, the decision model comprehensively understands the task situation and current state to make the most realistic planning decision. On the EgoPlan-Test set, EPD achieves a planning accuracy of 53.85% over 1,584 egocentric task planning questions. We have made all codes available at https://github.com/Kkskkkskr/EPD .","url_abs":"https://arxiv.org/abs/2407.19510v1","url_pdf":"https://arxiv.org/pdf/2407.19510v1.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":"epd-long-term-memory-extraction-context","repo_url":"https://github.com/kkskkkskr/epd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"task-planning","task_name":"Task Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.19510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19510"}},"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/Kkskkkskr/EPD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kkskkkskr/epd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"9ca69cb7bb5b1b9c","entry":"gpt4","repo":"kkskkkskr/epd","repo_kind":"official","path":"gpt4o_extraction.py","file_url":"https://github.com/kkskkkskr/epd/blob/HEAD/gpt4o_extraction.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":"9ca69cb7bb5b1b9c"}},{"code_sha256_prefix":"cc2eae88f453ec46","entry":"gpt4","repo":"Kkskkkskr/EPD","repo_kind":"official","path":"GPT_decision.py","file_url":"https://github.com/Kkskkkskr/EPD/blob/HEAD/GPT_decision.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":"cc2eae88f453ec46"}},{"code_sha256_prefix":"fbdfbd1a6fd76d37","entry":"gpt4","repo":"Kkskkkskr/EPD","repo_kind":"official","path":"claude_planning.py","file_url":"https://github.com/Kkskkkskr/EPD/blob/HEAD/claude_planning.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":"fbdfbd1a6fd76d37"}},{"code_sha256_prefix":"0b608023655e69c8","entry":"llm_inference","repo":"kkskkkskr/epd","repo_kind":"official","path":"gpt4o_extraction.py","file_url":"https://github.com/kkskkkskr/epd/blob/HEAD/gpt4o_extraction.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":"0b608023655e69c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}