TensorX
返回文献探索

Paper · arXiv 2509.09675

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, Dong Yu

28 upvotesSeptember 11, 2025arXiv 预印本
AI 摘要

Curiosity-Driven Exploration (CDE) enhances Reinforcement Learning with Verifiable Rewards (RLVR) by using intrinsic curiosity signals from the actor and critic to improve exploration and reduce premature convergence in Large Language Models (LLMs).

Reinforcement Learning with Verifiable RewardsRLVRLarge Language ModelsLLMsCuriosity-Driven ExplorationCDEactorcriticperplexityvalue estimatesmulti-head architectureexploration bonusoverconfident errorsdiversitycount-based exploration bonuscalibration collapse

Abstract

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy collapse. To address this challenge, we introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration. We formalize curiosity with signals from both the actor and the critic: for the actor, we use perplexity over its generated response, and for the critic, we use the variance of value estimates from a multi-head architecture. Both signals serve as an exploration bonus within the RLVR framework to guide the model. Our theoretical analysis shows that the actor-wise bonus inherently penalizes overconfident errors and promotes diversity among correct responses; moreover, we connect the critic-wise bonus to the well-established count-based exploration bonus in RL. Empirically, our method achieves an approximate +3 point improvement over standard RLVR using GRPO/PPO on AIME benchmarks. Further analysis identifies a calibration collapse mechanism within RLVR, shedding light on common LLM failure modes.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号