{"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/llm-powered-hierarchical-language-agent-for","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","arxiv_id":"2312.15224","date":"2023-12-23","proceeding":null,"authors":["Jijia Liu","Chao Yu","Jiaxuan Gao","Yuqing Xie","Qingmin Liao","Yi Wu","Yu Wang"],"abstract":"AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking LLM APIs and employing artificially designed complex prompts, which results in high inference latency. While this paradigm works well in scenarios with minimal interactive demands, such as code generation, it is unsuitable for highly interactive and real-time applications, such as gaming. Traditional gaming AI often employs small models or reactive policies, enabling fast inference but offering limited task completion and interaction abilities. In this work, we consider Overcooked as our testbed where players could communicate with natural language and cooperate to serve orders. We propose a Hierarchical Language Agent (HLA) for human-AI coordination that provides both strong reasoning abilities while keeping real-time execution. In particular, HLA adopts a hierarchical framework and comprises three modules: a proficient LLM, referred to as Slow Mind, for intention reasoning and language interaction, a lightweight LLM, referred to as Fast Mind, for generating macro actions, and a reactive policy, referred to as Executor, for transforming macro actions into atomic actions. Human studies show that HLA outperforms other baseline agents, including slow-mind-only agents and fast-mind-only agents, with stronger cooperation abilities, faster responses, and more consistent language communications.","url_abs":"https://arxiv.org/abs/2312.15224v2","url_pdf":"https://arxiv.org/pdf/2312.15224v2.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":"llm-powered-hierarchical-language-agent-for","repo_url":"https://github.com/HosnLS/Hierarchical-Language-Agent","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.15224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15224"}},"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/HosnLS/Hierarchical-Language-Agent","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"d8718f3775aebef5","entry":"bfs_search","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/executor/low.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/executor/low.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d8718f3775aebef5"}},{"code_sha256_prefix":"8265483c77251ae0","entry":"prep_mov_hist","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/mind/prompt.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/mind/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8265483c77251ae0"}},{"code_sha256_prefix":"357b20837cded5a1","entry":"prompt_order","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/mind/prompt.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/mind/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"357b20837cded5a1"}},{"code_sha256_prefix":"56e5079d67af6da4","entry":"prompt_order_int","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/mind/prompt.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/mind/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"56e5079d67af6da4"}},{"code_sha256_prefix":"eedfc3b390c9d4df","entry":"with_retry","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/mind/llm_api.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/mind/llm_api.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"eedfc3b390c9d4df"}},{"code_sha256_prefix":"bf22998fed26dc76","entry":"bfs_reachable","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/executor/low.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/executor/low.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bf22998fed26dc76"}},{"code_sha256_prefix":"c6b7087ec6b36da6","entry":"bfs_search_all","repo":"HosnLS/Hierarchical-Language-Agent","repo_kind":"official","path":"agent/agent/executor/low.py","file_url":"https://github.com/HosnLS/Hierarchical-Language-Agent/blob/HEAD/agent/agent/executor/low.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c6b7087ec6b36da6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}