Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Lagzian, A., Anumasa, S., & Liu, D. (2026). MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance. https://omanscience.com/en/articles/mirage-multi-perspective-creative-language-model-reasoning-with-reinforcement-learning-guidance
MLA 9
Lagzian, Arash, et al. "MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance." https://omanscience.com/en/articles/mirage-multi-perspective-creative-language-model-reasoning-with-reinforcement-learning-guidance.
Chicago (author–date)
Lagzian, Arash, Srinivas Anumasa, and Dianbo Liu. 2026. "MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance." https://omanscience.com/en/articles/mirage-multi-perspective-creative-language-model-reasoning-with-reinforcement-learning-guidance.
Harvard
Lagzian, A., Anumasa, S. and Liu, D. (2026) 'MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance', Available at: https://omanscience.com/en/articles/mirage-multi-perspective-creative-language-model-reasoning-with-reinforcement-learning-guidance.
Vancouver
Lagzian A, Anumasa S, Liu D. MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance. https://omanscience.com/en/articles/mirage-multi-perspective-creative-language-model-reasoning-with-reinforcement-learning-guidance
IEEE
A. Lagzian, S. Anumasa, and D. Liu, "MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance," https://omanscience.com/en/articles/mirage-multi-perspective-creative-language-model-reasoning-with-reinforcement-learning-guidance.