Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
Abstract
Critique-GRPO, an RL framework combining numerical and natural language feedback, enhances LLM reasoning across tasks and outperforms existing methods.
Recent advances in reinforcement learning (RL) with numerical feedback, such as scalar rewards, have significantly enhanced the complex reasoning capabilities of large language models (LLMs). Despite this success, we identify three key challenges encountered by RL with solely numerical feedback: performance plateaus, limited effectiveness of self-reflection, and persistent failures. We then demonstrate that RL-finetuned models, even after exhibiting performance plateaus, can generate correct refinements on persistently failed problems by leveraging natural language feedback in the form of critiques. Building on this insight, we propose Critique-GRPO, an online RL framework that integrates both natural language and numerical feedback for effective policy optimization. Critique-GRPO enables LLMs to learn from initial responses and critique-guided refinements simultaneously while maintaining exploration. Extensive experiments using Qwen2.5-7B-Base and Qwen3-8B-Base show that Critique-GRPO consistently outperforms supervised learning-based and RL-based fine-tuning approaches across eight challenging mathematical, STEM, and general reasoning tasks, improving average pass@1 scores by approximately 4.5% and 5%, respectively. Notably, Critique-GRPO surpasses a strong baseline that incorporates expert demonstrations within online RL. Further analysis reveals two critical insights about policy exploration: (1) higher entropy does not always guarantee efficient learning from exploration, and (2) longer responses do not necessarily lead to more effective exploration.
Community
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models (2025)
- Behavior Injection: Preparing Language Models for Reinforcement Learning (2025)
- Incentivizing Strong Reasoning from Weak Supervision (2025)
- KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning (2025)
- RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning (2025)
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning (2025)
- Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper