Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewards and weak credit assignment, resulting in ambiguous optimization signals and underutilization of the useful information embedded in failed trajectories. To address this challenge, we propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision, without relying on any external signals. By jointly optimizing correction samples derived from the model's own failed attempts together with the standard RLVR objective, CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors. Extensive experiments across 11 benchmarks spanning mathematical reasoning and code generation demonstrate that CIPO consistently and significantly outperforms strong baselines in both reasoning and correction performance. Moreover, CIPO yields stronger pass@K gains, indicating that it improves the model's intrinsic reasoning capacity rather than merely redistributing probability mass over existing correct answers.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningMathematical ReasoningCode GenerationSimilar Papers 제목 키워드 기반
DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a leading paradigm for enhancing visual reasoning in Multimodal Large Language Models (MLLMs). However, existing RLVR methods optimize primarily for th…
Reinforcement LearningMathematical ReasoningVisual ReasoningReinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitab…
Reinforcement LearningNo Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS
Recent work reports gains in neural text-to-speech (TTS) with Group Relative Policy Optimization (GRPO). However, in the absence of a verifiable reward for \textit{prosody}, GRPO trained on transcription-oriented signals…
Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOTA reasoning models, is highly sensitive to noise from inconsistent or erroneou…
Reinforcement LearningWMPO: World Model-based Policy Optimization for Vision-Language-Action Models
Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation, but their reliance on expert demonstrations limits their ability to learn from failures and perform self-correctio…
Reinforcement Learning