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

• URL: http://arxiv.org/abs/2505.10425v2
• Date: Sun, 18 May 2025 07:34:17 GMT
• Title: Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
• Authors: Jingyao Wang, Wenwen Qiang, Zeen Song, Changwen Zheng, Hui Xiong,
• Abstract summary: Large language models (LLMs) excel at complex tasks thanks to advances in reasoning abilities.<n>Existing methods overlook the trade-off between reasoning effectiveness and computational efficiency.<n>We propose Learning to Think to make the models achieve optimal reasoning with fewer tokens.
• Score: 25.03191529055168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) excel at complex tasks thanks to advances in reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and computational 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.

Related papers

• ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization [16.51303604678232]
  Reasoning Compression ThroUgh Stepwise Trials (ReCUT) is a novel method aimed at balancing the accuracy and length of reasoning trajectory.<n> Experimental results across multiple math reasoning datasets and backbone models demonstrate that ReCUT significantly reduces reasoning lengths by approximately 30-50%.
  arXiv  Detail & Related papers  (2025-06-12T15:43:01Z)
• Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation [9.282278040339138]
  $textbfR2Rec$ is a reasoning-enhanced recommendation framework.<n>It samples interaction chains from the user-item graph and converts them into structured interaction-of-thoughts.
  arXiv  Detail & Related papers  (2025-06-05T14:16:44Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• Interleaved Reasoning for Large Language Models via Reinforcement Learning [22.403928213802036]
  Long chain-of-thought (CoT) enhances large language models' (LLM) reasoning capabilities.<n>We propose a novel training paradigm that uses reinforcement learning (RL) to guide reasoning LLMs to interleave thinking and answering for multi-hop questions.
  arXiv  Detail & Related papers  (2025-05-26T07:58:17Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Offline Reinforcement Learning for LLM Multi-Step Reasoning [15.687002884103537]
  OREO (Offline Reasoning Optimization) is an offline reinforcement learning method for enhancing multi-step reasoning.<n>It reduces the need to collect pairwise data and enables better credit assignment.<n>It surpasses existing offline learning methods on multi-step reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-12-20T18:49:45Z)
• Rational Metareasoning for Large Language Models [5.5539136805232205]
  Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs)<n>This work introduces a novel approach based on computational models of metareasoning used in cognitive science.<n>We develop a reward function that incorporates the Value of Computation by penalizing unnecessary reasoning.
  arXiv  Detail & Related papers  (2024-10-07T23:48:52Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.