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

2026-09-18

AI Summary

为解决大型语言模型处理复杂数学、科学和逻辑任务的问题，提出MIRAGE框架，通过选择有效视角并使用强化学习指导推理，提高了解决问题的准确性。

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.

Problem

• Large Language Models
• complex tasks
• mathematical
• scientific
• logical

Innovation

• Multi-perspective Inference
• Reinforcement Learning Guidance
• Cognitive Flexibility
• Selector and Reasoner Framework