paper-with-me

홈 › Papers

MARS: toward more efficient multi-agent collaboration for LLM reasoning

2025-09-24 · Xiao Wang, Jia Wang, Yijie Wang, Pengtao Dang, Sha Cao, Chi Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.20502

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation

2026-02-08 · Shijie Wang, Pengfei Li, Yikun Fu, Kaifeng Liu 외 arxiv

While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in complex tasks such as code generation. Mul…

Multi-agent Reinforcement LearningCode Generation

MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation

2026-04-16 · Pengfei Li, Shijie Wang, Fangyuan Li, Yikun Fu 외 arxiv

Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains …

Reinforcement LearningCode Generation

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

2025-10-17 · Huining Yuan, Zelai Xu, Zheyue Tan, Xiangmin Yi 외 arxiv

Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective…

Reinforcement Learning

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

2024-06-13 · CVPR 2024 1 · Yiming Li, Zhiheng Li, Nuo Chen, Moonjun Gong 외

Large-scale datasets have fueled recent advancements in AI-based autonomous vehicle research. However, these datasets are usually collected from a single vehicle's one-time pass of a certain location, lacking multiagent …

3D ReconstructionAutonomous VehiclesObject Discovery

MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism

2025-11-14 · Shulin Liu, Dong Du, Tao Yang, Yang Li 외 arxiv

Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reason…

Reinforcement Learning