{"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/meta-design-matters-a-self-design-multi-agent","title":"Meta-Design Matters: A Self-Design Multi-Agent System","arxiv_id":"2505.14996","date":"2025-05-21","proceeding":null,"authors":["Zixuan Ke","Austin Xu","Yifei Ming","Xuan-Phi Nguyen","Caiming Xiong","Shafiq Joty"],"abstract":"Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles and communication protocols. These manual designs often fail to align with the underlying LLMs' strengths and struggle to adapt to novel tasks. Recent automatic MAS approaches attempt to mitigate these limitations but typically necessitate a validation-set for tuning and yield static MAS designs lacking adaptability during inference. We introduce SELF-MAS, the first self-supervised, inference-time only framework for automatic MAS design. SELF-MAS employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance, without requiring a validation set. Critically, it enables dynamic agent composition and problem decomposition through meta-feedback on solvability and completeness. Experiments across math, graduate-level QA, and software engineering benchmarks, using both closed-source and open-source LLM back-bones of varying sizes, demonstrate that SELF-MAS outperforms both manual and automatic MAS baselines, achieving a 7.44% average accuracy improvement over the next strongest baseline while maintaining cost-efficiency. These findings underscore the promise of meta-level self-supervised design for creating effective and adaptive MAS.","url_abs":"https://arxiv.org/abs/2505.14996v1","url_pdf":"https://arxiv.org/pdf/2505.14996v1.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":"meta-design-matters-a-self-design-multi-agent","repo_url":"https://github.com/SalesforceAIResearch/MAS-Zero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"problem-decomposition","task_name":"Problem Decomposition"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"mas","method_name":"MAS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.14996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14996"}},"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/SWE-bench/SWE-bench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SalesforceAIResearch/MAS-Zero","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"2090e43062a53e84","entry":"forward","repo":"SalesforceAIResearch/MAS-Zero","repo_kind":"listed","path":"blocks/llm_debate.py","file_url":"https://github.com/SalesforceAIResearch/MAS-Zero/blob/HEAD/blocks/llm_debate.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":"2090e43062a53e84"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}