Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jingyao, Qiang, Wenwen, Song, Zeen, Zheng, Changwen, Xiong, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918160704208896
author Wang, Jingyao
Qiang, Wenwen
Song, Zeen
Zheng, Changwen
Xiong, Hui
author_facet Wang, Jingyao
Qiang, Wenwen
Song, Zeen
Zheng, Changwen
Xiong, Hui
contents Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long reasoning chains and wasting tokens. To address this, we propose Learning to Think (L2T), an information-theoretic reinforcement fine-tuning framework for LLMs to make the models achieve optimal reasoning with fewer tokens. Specifically, L2T treats each query-response interaction as a hierarchical session of multiple episodes and proposes a universal dense process reward, i.e., quantifies the episode-wise information gain in parameters, requiring no extra annotations or task-specific evaluators. We propose a method to quickly estimate this reward based on PAC-Bayes bounds and the Fisher information matrix. Theoretical analyses show that it significantly reduces computational complexity with high estimation accuracy. By immediately rewarding each episode's contribution and penalizing excessive updates, L2T optimizes the model via reinforcement learning to maximize the use of each episode and achieve effective updates. Empirical results on various reasoning benchmarks and base models demonstrate the advantage of L2T across different tasks, boosting both reasoning effectiveness and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
Wang, Jingyao
Qiang, Wenwen
Song, Zeen
Zheng, Changwen
Xiong, Hui
Machine Learning
Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long reasoning chains and wasting tokens. To address this, we propose Learning to Think (L2T), an information-theoretic reinforcement fine-tuning framework for LLMs to make the models achieve optimal reasoning with fewer tokens. Specifically, L2T treats each query-response interaction as a hierarchical session of multiple episodes and proposes a universal dense process reward, i.e., quantifies the episode-wise information gain in parameters, requiring no extra annotations or task-specific evaluators. We propose a method to quickly estimate this reward based on PAC-Bayes bounds and the Fisher information matrix. Theoretical analyses show that it significantly reduces computational complexity with high estimation accuracy. By immediately rewarding each episode's contribution and penalizing excessive updates, L2T optimizes the model via reinforcement learning to maximize the use of each episode and achieve effective updates. Empirical results on various reasoning benchmarks and base models demonstrate the advantage of L2T across different tasks, boosting both reasoning effectiveness and efficiency.
title Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
topic Machine Learning
url https://arxiv.org/abs/2505.10425