MeRF: Motivation-enhanced Reinforcement Finetuning for Large Reasoning Models

• URL: http://arxiv.org/abs/2506.18485v1
• Date: Mon, 23 Jun 2025 10:37:57 GMT
• Title: MeRF: Motivation-enhanced Reinforcement Finetuning for Large Reasoning Models
• Authors: Junjie Zhang, Guozheng Ma, Shunyu Liu, Haoyu Wang, Jiaxing Huang, Ting-En Lin, Fei Huang, Yongbin Li, Dacheng Tao,
• Abstract summary: Motivation-enhanced Reinforcement Finetuning (MeRF) is an intuitive yet effective method enhancing reinforcement learning of Large Language Models (LLMs)<n>MeRF directly injects the reward specification into the prompt, which serves as an in-context motivation for model to improve its responses with awareness of the optimization objective.<n> Empirical evaluations on the Knights and Knaves(K&K) logic puzzle reasoning benchmark demonstrate that textttMeRF achieves substantial performance gains over baselines.
• Score: 95.6332110724999
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful learn-to-reason paradigm for Large Language Models (LLMs) to tackle complex reasoning tasks. However, existing RLVR methods overlook one of the most distinctive capabilities of LLMs, their in-context learning ability, as prominently demonstrated by the success of Chain-of-Thought (CoT) prompting. This motivates us to explore how reinforcement learning can be effectively combined with in-context learning to better improve the reasoning capabilities of LLMs. In this paper, we introduce Motivation-enhanced Reinforcement Finetuning} (MeRF), an intuitive yet effective method enhancing reinforcement learning of LLMs by involving ``telling LLMs the rules of the game''. Specifically, MeRF directly injects the reward specification into the prompt, which serves as an in-context motivation for model to improve its responses with awareness of the optimization objective. This simple modification leverages the in-context learning ability of LLMs aligning generation with optimization, thereby incentivizing the model to generate desired outputs from both inner motivation and external reward. Empirical evaluations on the Knights and Knaves~(K&K) logic puzzle reasoning benchmark demonstrate that \texttt{MeRF} achieves substantial performance gains over baselines. Moreover, ablation studies show that performance improves with greater consistency between the in-context motivation and the external reward function, while the model also demonstrates an ability to adapt to misleading motivations through reinforcement learning.

Related papers

• No Free Lunch: Rethinking Internal Feedback for LLM Reasoning [12.881043910316787]
  Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning.<n>We investigate an alternative class of methods, Reinforcement Learning from Internal Feedback (RLIF), which relies solely on intrinsic model-derived signals instead of external rewards.
  arXiv  Detail & Related papers  (2025-06-20T17:59:52Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning [87.7836502955847]
  We propose a novel self-rewarding reinforcement learning framework to enhance Large Language Model (LLM) reasoning.<n>Our key insight is that correct responses often exhibit consistent trajectory patterns in terms of model likelihood.<n>We introduce CoVo, an intrinsic reward mechanism that integrates Consistency and Volatility via a robust vector-space aggregation strategy.
  arXiv  Detail & Related papers  (2025-06-10T12:40:39Z)
• KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation [78.96590724864606]
  We introduce the Knowledge Orthogonal Reasoning Gymnasium (KORGym), a dynamic evaluation platform inspired by KOR-Bench and Gymnasium.<n>KORGym offers over fifty games in either textual or visual formats and supports interactive, multi-turn assessments with reinforcement learning scenarios.
  arXiv  Detail & Related papers  (2025-05-20T16:06:32Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• FANformer: Improving Large Language Models Through Effective Periodicity Modeling [30.84203256282429]
  We introduce FANformer, which adapts Fourier Analysis Network (FAN) into attention mechanism to achieve efficient periodicity modeling.<n>We show that FANformer consistently outperforms Transformer when scaling up model size and training tokens.<n>Our pretrained FANformer-1B exhibits marked improvements on downstream tasks compared to open-source LLMs with similar model parameters or training tokens.
  arXiv  Detail & Related papers  (2025-02-28T18:52:24Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning [6.691759477350243]
  Large language models (LLMs) trained with Reinforcement Learning from Human Feedback have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque.<n>This paper introduces a novel approach to interpreting LLMs by applying inverse reinforcement learning (IRL) to recover their implicit reward functions.<n>We conduct experiments on toxicity-aligned LLMs of varying sizes, extracting reward models that achieve up to 85% accuracy in predicting human preferences.
  arXiv  Detail & Related papers  (2024-10-16T12:14:25Z)
• Enhancing Q-Learning with Large Language Model Heuristics [0.0]
  Large language models (LLMs) can achieve zero-shot learning for simpler tasks, but they suffer from low inference speeds and occasional hallucinations. We propose textbfLLM-guided Q-learning, a framework that leverages LLMs as hallucinations to aid in learning the Q-function for reinforcement learning.
  arXiv  Detail & Related papers  (2024-05-06T10:42:28Z)
• Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection [24.435121488662897]
  We propose a novel framework: Reinforcement Learning from Reflective Feedback (RLRF) RLRF employs a self-reflection mechanism to systematically explore and refine LLM responses, then fine-tuning the models via a RL algorithm along with promising responses. Our experiments across Just-Eval, Factuality, and Mathematical Reasoning demonstrate the efficacy and transformative potential of RLRF.
  arXiv  Detail & Related papers  (2024-03-21T08:57:27Z)

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.