# MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs

Source: [MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs](<https://www.sota2.com/research/paper/694cc4e653fdd5c36173a65a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-10T05:01:35.776Z

Authors: Onat Ozer, Yuchen Wang, Grace Wu, Daniel Dosti, Honghao Zhang, Vivi De La Rue

Published: 2025-12-23T23:47:31.000Z

## Abstract

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exhibit degeneration of thought, where the LLM continues to repeat the same errors again and again even with the knowledge that its wrong. To address this problem, we instead introduce multi-agent with multi-persona debators as the method to generate reflections. Through out extensive experimentation, we've found that the leads to better diversity of in the reflections generated by the llm agent. We demonstrate an accuracy of 47% EM HotPot QA (question answering) and 82.7% on HumanEval (programming), both performances surpassing reflection with a single llm.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.20845>)

[PDF](<https://arxiv.org/pdf/2512.20845.pdf>)
