{"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/implicitly-aligning-humans-and-autonomous","title":"Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions","arxiv_id":"2505.04579","date":"2025-05-07","proceeding":null,"authors":["Stéphane Aroca-Ouellette","Miguel Aroca-Ouellette","Katharina von der Wense","Alessandro Roncone"],"abstract":"In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA$^2$: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA$^2$ in the Overcooked environment, demonstrating statistically significant improvement over existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2505.04579v1","url_pdf":"https://arxiv.org/pdf/2505.04579v1.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":"implicitly-aligning-humans-and-autonomous","repo_url":"https://github.com/HIRO-group/HA2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hierarchical-reinforcement-learning","task_name":"Hierarchical Reinforcement Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.04579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04579"}},"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/HIRO-group/HA2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"7f363f0bfb29bb68","entry":"calculate_completed_subtask","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/common/subtasks.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/common/subtasks.py","link_basis":"harvester_set","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":"7f363f0bfb29bb68"}},{"code_sha256_prefix":"d153b6200f2028a4","entry":"facing","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/common/subtasks.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/common/subtasks.py","link_basis":"harvester_set","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":"d153b6200f2028a4"}},{"code_sha256_prefix":"f2a10fbe35283d71","entry":"get_args_to_save","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/common/arguments.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/common/arguments.py","link_basis":"harvester_set","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":"f2a10fbe35283d71"}},{"code_sha256_prefix":"5f6d9fe3bb842d1a","entry":"get_arguments","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/common/arguments.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/common/arguments.py","link_basis":"harvester_set","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":"5f6d9fe3bb842d1a"}},{"code_sha256_prefix":"99ea6ca6b4ffdecb","entry":"get_output_shape","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/common/networks.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/common/networks.py","link_basis":"harvester_set","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":"99ea6ca6b4ffdecb"}},{"code_sha256_prefix":"89af046dbb6e6088","entry":"is_held_obj","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/agents/agent_utils.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/agents/agent_utils.py","link_basis":"harvester_set","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":"89af046dbb6e6088"}},{"code_sha256_prefix":"52245215641e4c82","entry":"non_full_pot_exists","repo":"HIRO-group/HA2","repo_kind":"official","path":"oai_agents/common/subtasks.py","file_url":"https://github.com/HIRO-group/HA2/blob/HEAD/oai_agents/common/subtasks.py","link_basis":"harvester_set","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":"52245215641e4c82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}