{"ID":2866764,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20502","arxiv_id":"2509.20502","title":"MARS: toward more efficient multi-agent collaboration for LLM reasoning","abstract":"Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this limitation by enabling collaborative reasoning among multiple models in a round-table debate manner. While effective, MAD introduces substantial computational overhead due to the number of agents involved and the frequent communication required. In this paper, we propose MARS (Multi-Agent Review System), a role-based collaboration framework inspired by the review process. In MARS, an author agent generates an initial solution, reviewer agents provide decisions and comments independently, and a meta-reviewer integrates the feedback to make the final decision and guide further revision. This design enhances reasoning quality while avoiding costly reviewer-to-reviewer interactions, thereby controlling token consumption and inference time. We compared MARS with both MAD and other state-of-the-art reasoning strategies across multiple benchmarks. Extensive experiments with different LLMs show that MARS matches the accuracy of MAD while reducing both token usage and inference time by approximately 50\\%. Code is available at https://github.com/xwang97/MARS.","short_abstract":"Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this limitation by enabling collaborative reasoning among multiple models in a round-tab...","url_abs":"https://arxiv.org/abs/2509.20502","url_pdf":"https://arxiv.org/pdf/2509.20502v2","authors":"[\"Xiao Wang\",\"Jia Wang\",\"Yijie Wang\",\"Pengtao Dang\",\"Sha Cao\",\"Chi Zhang\"]","published":"2025-09-24T19:24:33Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":609408,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2866764,"paper_url":"https://arxiv.org/abs/2509.20502","paper_title":"MARS: toward more efficient multi-agent collaboration for LLM reasoning","repo_url":"https://github.com/xwang97/MARS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}