# Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning

arXiv: https://arxiv.org/abs/2402.14963 · HTML: https://mlsanity.com/paper/2402.14963/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 15 of 15)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [Small Models are Valuable Plug-ins for Large Language Models](https://mlsanity.com/paper/2305.08848/) (2023)
- [C-MCTS: Safe Planning with Monte Carlo Tree Search](https://mlsanity.com/paper/2305.16209/) (2023)

## Built on by (most cited first, 10 of 10)

- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)
- [OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System](https://mlsanity.com/paper/2509.18091/) (2025)
- [Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge](https://mlsanity.com/paper/2602.09341/) (2026)
- [EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving](https://mlsanity.com/paper/2506.02672/) (2025)
- [SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding](https://mlsanity.com/paper/2406.18200/) (2024)
- [A Survey of Calibration Process for Black-Box LLMs](https://mlsanity.com/paper/2412.12767/) (2024)
- [WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation](https://mlsanity.com/paper/2503.19065/) (2025)
- [MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models](https://mlsanity.com/paper/2510.24794/) (2025)
- [RE-AD: Real-Time Requirement Adherence for Data Labeling](https://mlsanity.com/paper/2607.20455/) (2026)
- [When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models](https://mlsanity.com/paper/2610.07018/) (2026)

## Abstract (arXiv)

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources. In addition to the inefficiency of LLMs in self-assessment, we also observe that LLMs struggle to revisit their predictions despite receiving explicit negative feedback. Therefore, We propose Mirror, a Multiple-perspective self-reflection method for knowledge-rich reasoning, to avoid getting stuck at a particular reflection iteration. Mirror enables LLMs to reflect from multiple-perspective clues, achieved through a heuristic interaction between a Navigator and a Reasoner. It guides agents toward diverse yet plausibly reliable reasoning trajectory without access to ground truth by encouraging (1) diversity of directions generated by Navigator and (2) agreement among strategically induced perturbations in responses generated by the Reasoner. The experiments on five reasoning datasets demonstrate that Mirror's superiority over several contemporary self-reflection approaches. Additionally, the ablation study studies clearly indicate that our strategies alleviate the aforementioned challenges.