# MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance

arXiv: https://arxiv.org/abs/2609.21554 · HTML: https://mlsanity.com/paper/2609.21554/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 11 of its 58 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 11 of 11)

- [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)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows](https://mlsanity.com/paper/2409.17433/) (2024)
- [When is the partial map classifier a Sierpi'nski cone?](https://mlsanity.com/paper/2504.06789/) (2025)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have revolutionized artificial intelligence and how human interact with AIs. Despite impressive advancements, LLMs struggle with complex mathematical, scientific, and logical tasks. Inspired by human cognitive flexibility - our ability to dynamically switch mental perspectives - we propose MIRAGE (Multi-perspective Inference-time Reasoning via Agent-Guided Exploration), a novel inference-time creative thinking framework. MIRAGE includes a Selector that prioritizes effective conceptual perspectives (e.g., algebraic, probabilistic) and a Reasoner that sequentially solves tasks until a confident solution emerges, otherwise aggregating multiple perspectives. Tested on GSM8K, MATH500, MMLU-Pro, and Game-of-24 benchmarks, MIRAGE consistently outperforms methods like Chain-of-Thought and diverse prompting ensembles, significantly boosting accuracy with minimal inference overhead, providing a scalable solution for practical applications.