{"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/adaptive-in-conversation-team-building-for","title":"Adaptive In-conversation Team Building for Language Model Agents","arxiv_id":"2405.19425","date":"2024-05-29","proceeding":null,"authors":["Linxin Song","Jiale Liu","Jieyu Zhang","Shaokun Zhang","Ao Luo","Shijian Wang","Qingyun Wu","Chi Wang"],"abstract":"Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks, while the effective design of multiple agents for a particular application remains an art. It is thus intriguing to answer a critical question: Given a task, how can we build a team of LLM agents to solve it effectively? Our new adaptive team-building paradigm offers a flexible solution, realized through a novel agent design named Captain Agent. It dynamically forms and manages teams for each step of a task-solving process, utilizing nested group conversations and reflection to ensure diverse expertise and prevent stereotypical outputs, allowing for a flexible yet structured approach to problem-solving. A comprehensive evaluation across six real-world scenarios demonstrates that Captain Agent significantly outperforms existing multi-agent methods with 21.94% improvement in average accuracy, providing outstanding performance without requiring task-specific prompt engineering. Our exploration of different backbone LLM and cost analysis further shows that Captain Agent can improve the conversation quality of weak LLM and achieve competitive performance with extremely low cost, which illuminates the application of multi-agent systems.","url_abs":"https://arxiv.org/abs/2405.19425v2","url_pdf":"https://arxiv.org/pdf/2405.19425v2.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":"adaptive-in-conversation-team-building-for","repo_url":"https://github.com/ag2ai/ag2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.19425","atlas_url":"https://app.syntology.ai/?focus=2405.19425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19425"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ag2ai/ag2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"4ef11c99a05fb0d3","entry":"close_unanswered_tool_calls","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/history.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/history.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ef11c99a05fb0d3"}},{"code_sha256_prefix":"0b66e78733b6fa05","entry":"get_missing_imports","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/_import_utils.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/_import_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b66e78733b6fa05"}},{"code_sha256_prefix":"4f0a5a72c05098a4","entry":"missing_additional_dependency","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/exceptions.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/exceptions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f0a5a72c05098a4"}},{"code_sha256_prefix":"6a15da2c46cc02e1","entry":"missing_optional_dependency","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/exceptions.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/exceptions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a15da2c46cc02e1"}},{"code_sha256_prefix":"4d3bf98e05bfb046","entry":"patch_object","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/_import_utils.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/_import_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d3bf98e05bfb046"}},{"code_sha256_prefix":"c85f19bbfd003ea2","entry":"require_optional_import","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/_import_utils.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/_import_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c85f19bbfd003ea2"}},{"code_sha256_prefix":"ae48d965eef3a01c","entry":"unanswered_tool_calls","repo":"ag2ai/ag2","repo_kind":"official","path":"ag2/history.py","file_url":"https://github.com/ag2ai/ag2/blob/HEAD/ag2/history.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ae48d965eef3a01c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}