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

arXiv: https://arxiv.org/abs/2509.20502 · HTML: https://mlsanity.com/paper/2509.20502/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners](https://mlsanity.com/paper/2406.11050/) (2024)
- [AgentRefine: Enhancing Agent Generalization through Refinement Tuning](https://mlsanity.com/paper/2501.01702/) (2025)
- [Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage](https://mlsanity.com/paper/2412.15606/) (2024)
- [MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification](https://mlsanity.com/paper/2502.13383/) (2025)
- [ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification](https://mlsanity.com/paper/2502.14565/) (2025)
- [Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning](https://mlsanity.com/paper/2502.13820/) (2025)
- [LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning](https://mlsanity.com/paper/2506.07443/) (2025)
- [Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision](https://mlsanity.com/paper/2505.20415/) (2025)

## Built on by (most cited first, 13 of 13)

- [Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge](https://mlsanity.com/paper/2602.09341/) (2026)
- [Toward Efficient Agents: Memory, Tool learning, and Planning](https://mlsanity.com/paper/2601.14192/) (2026)
- [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://mlsanity.com/paper/2602.03955/) (2026)
- [Scaling Discovery through Test-Time Communication](https://mlsanity.com/paper/2609.21032/) (2026)
- [DIAGPaper: Diagnosing Valid and Specific Weaknesses in Scientific Papers via Multi-Agent Reasoning](https://mlsanity.com/paper/2601.07611/) (2026)
- [Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems](https://mlsanity.com/paper/2606.04306/) (2026)
- [HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate](https://mlsanity.com/paper/2604.09679/) (2026)
- [An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing](https://mlsanity.com/paper/2605.13221/) (2026)
- [Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages](https://mlsanity.com/paper/2608.14375/) (2026)
- [Persona-based Multi-Agent Collaboration for Brainstorming](https://mlsanity.com/paper/2512.04488/) (2025)
- [Tandem Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2606.28166/) (2026)
- [A Comprehensive Study of Implementation Bugs in Multi-modal Agents](https://mlsanity.com/paper/2607.04974/) (2026)
- [Adversarial Review: Structured Disagreement for Grounded Agentic Code Review](https://mlsanity.com/paper/2608.18167/) (2026)

## Abstract (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.