{"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/sirius-self-improving-multi-agent-systems-via","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","arxiv_id":"2502.04780","date":"2025-02-07","proceeding":null,"authors":["Wanjia Zhao","Mert Yuksekgonul","Shirley Wu","James Zou"],"abstract":"Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prompts and heuristics, making optimization difficult. A key challenge in optimizing multi-agent systems is acquiring suitable training data for specialized agents. We introduce SiriuS, a self-improving, reasoning-driven optimization framework for multi-agent systems. Central to our approach is the construction of an experience library: a repository of high-quality reasoning trajectories. The library is built by retaining reasoning steps that lead to successful outcomes, providing a robust training set for optimizing multi-agent system. Additionally, we introduce a library augmentation procedure that refines unsuccessful trajectories, further enriching the library. SiriuS boosts performance by 2.86\\% to 21.88\\% on reasoning and biomedical QA and enhances agent negotiation in competitive settings. Our results show that SiriuS enhances multi-agent performance while generating reusable data for self-correction and self-play enhancement in the future.","url_abs":"https://arxiv.org/abs/2502.04780v1","url_pdf":"https://arxiv.org/pdf/2502.04780v1.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":"sirius-self-improving-multi-agent-systems-via","repo_url":"https://github.com/zou-group/sirius","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":null,"method_name":"Library"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.04780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04780"}},"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/zou-group/sirius","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"9cb8583baa1fb871","entry":"extract_answer_letter","repo":"zou-group/sirius","repo_kind":"official","path":"libs/data_loader.py","file_url":"https://github.com/zou-group/sirius/blob/HEAD/libs/data_loader.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":"9cb8583baa1fb871"}},{"code_sha256_prefix":"729efb31374ad186","entry":"extract_answer_number","repo":"zou-group/sirius","repo_kind":"official","path":"libs/data_loader.py","file_url":"https://github.com/zou-group/sirius/blob/HEAD/libs/data_loader.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":"729efb31374ad186"}},{"code_sha256_prefix":"804abe4d4e124336","entry":"extract_answer_true_false","repo":"zou-group/sirius","repo_kind":"official","path":"Actor_Critic/get_critic_judegement.py","file_url":"https://github.com/zou-group/sirius/blob/HEAD/Actor_Critic/get_critic_judegement.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":"804abe4d4e124336"}},{"code_sha256_prefix":"186d450270e69563","entry":"extract_answer_yesno","repo":"zou-group/sirius","repo_kind":"official","path":"libs/data_loader.py","file_url":"https://github.com/zou-group/sirius/blob/HEAD/libs/data_loader.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":"186d450270e69563"}},{"code_sha256_prefix":"7291e45aa1567866","entry":"get_rephrase_response","repo":"zou-group/sirius","repo_kind":"official","path":"Actor_Critic/get_critic_regenerate.py","file_url":"https://github.com/zou-group/sirius/blob/HEAD/Actor_Critic/get_critic_regenerate.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":"7291e45aa1567866"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}