{"work":{"id":"749a42f9-4e3e-42a9-b050-d9e44b9719e8","openalex_id":"https://openalex.org/W4407247211","doi":"10.48550/arxiv.2502.04180","arxiv_id":"2502.04180","raw_key":null,"title":"Multi-agent Architecture Search via Agentic Supernet","authors":null,"authors_text":"Guibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang, Lei Bai, and Xiang Wang","year":2025,"venue":"cs.LG","abstract":"Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs. Despite the availability of methods to automate the design of agentic workflows, they typically seek to identify a static, complex, one-size-fits-all system, which, however, fails to dynamically allocate inference resources based on the difficulty and domain of each query. To address this challenge, we shift away from the pursuit of a monolithic agentic system, instead optimizing the \\textbf{agentic supernet}, a probabilistic and continuous distribution of agentic architectures. We introduce MaAS, an automated framework that samples query-dependent agentic systems from the supernet, delivering high-quality solutions and tailored resource allocation (\\textit{e.g.}, LLM calls, tool calls, token cost). Comprehensive evaluation across six benchmarks demonstrates that MaAS \\textbf{(I)} requires only $6\\sim45\\%$ of the inference costs of existing handcrafted or automated multi-agent systems, \\textbf{(II)} surpasses them by $0.54\\%\\sim11.82\\%$, and \\textbf{(III)} enjoys superior cross-dataset and cross-LLM-backbone transferability.","external_url":"https://arxiv.org/abs/2502.04180","cited_by_count":0,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2502.04180","created_at":"2026-05-10T00:19:46.411678+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Zhang, L","render_title":"Zhang, L"},"hub":{"state":{"work_id":"749a42f9-4e3e-42a9-b050-d9e44b9719e8","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":23,"external_cited_by_count":0,"distinct_field_count":9,"first_pith_cited_at":"2025-07-28T17:55:08+00:00","last_pith_cited_at":"2026-07-08T02:57:22+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-21T07:49:38.559682+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":5}],"polarity_counts":[{"context_polarity":"background","n":5}],"runs":{},"summary":{},"graph":{},"authors":[]}}