{"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/epo-hierarchical-llm-agents-with-environment","title":"EPO: Hierarchical LLM Agents with Environment Preference Optimization","arxiv_id":"2408.16090","date":"2024-08-28","proceeding":null,"authors":["Qi Zhao","Haotian Fu","Chen Sun","George Konidaris"],"abstract":"Long-horizon decision-making tasks present significant challenges for LLM-based agents due to the need for extensive planning over multiple steps. In this paper, we propose a hierarchical framework that decomposes complex tasks into manageable subgoals, utilizing separate LLMs for subgoal prediction and low-level action generation. To address the challenge of creating training signals for unannotated datasets, we develop a reward model that leverages multimodal environment feedback to automatically generate reward signals. We introduce Environment Preference Optimization (EPO), a novel method that generates preference signals from the environment's feedback and uses them to train LLM-based agents. Extensive experiments on ALFRED demonstrate the state-of-the-art performance of our framework, achieving first place on the ALFRED public leaderboard and showcasing its potential to improve long-horizon decision-making in diverse environments.","url_abs":"https://arxiv.org/abs/2408.16090v2","url_pdf":"https://arxiv.org/pdf/2408.16090v2.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":"epo-hierarchical-llm-agents-with-environment","repo_url":"https://github.com/kevinz8866/epo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.16090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16090"}},"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/kevinz8866/epo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/kevinz8866/EPO","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"214442c552c26bab","entry":"get_parameter_names","repo":"kevinz8866/EPO","repo_kind":"official","path":"utils/model_utils.py","file_url":"https://github.com/kevinz8866/EPO/blob/HEAD/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"214442c552c26bab"}},{"code_sha256_prefix":"fd9eba78d468ef8e","entry":"construct_optimizer","repo":"kevinz8866/EPO","repo_kind":"official","path":"optimizers/optimizer.py","file_url":"https://github.com/kevinz8866/EPO/blob/HEAD/optimizers/optimizer.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":"fd9eba78d468ef8e"}},{"code_sha256_prefix":"5f59cc6076a39cbf","entry":"get_dm","repo":"kevinz8866/EPO","repo_kind":"official","path":"datasets/get_datamodule.py","file_url":"https://github.com/kevinz8866/EPO/blob/HEAD/datasets/get_datamodule.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":"5f59cc6076a39cbf"}},{"code_sha256_prefix":"d363e52ca1709853","entry":"load_config","repo":"kevinz8866/EPO","repo_kind":"official","path":"parser.py","file_url":"https://github.com/kevinz8866/EPO/blob/HEAD/parser.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":"d363e52ca1709853"}},{"code_sha256_prefix":"7baf2bbceb261d8b","entry":"lr_factory","repo":"kevinz8866/EPO","repo_kind":"official","path":"optimizers/lr_scheduler.py","file_url":"https://github.com/kevinz8866/EPO/blob/HEAD/optimizers/lr_scheduler.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":"7baf2bbceb261d8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}