The following papers were recommended by the Semantic Scholar API
\n- \n
- VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning (2025) \n
- Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner (2025) \n
- Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning (2025) \n
- RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback (2025) \n
- Train Long, Think Short: Curriculum Learning for Efficient Reasoning (2025) \n
- Diversity-Enhanced Reasoning for Subjective Questions (2025) \n
- JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Abstract
Parallel-R1, a reinforcement learning framework, enhances large language models' reasoning capabilities by enabling parallel thinking through a progressive curriculum, leading to significant performance improvements on math benchmarks.
Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose Parallel-R1, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model's thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a mid-training exploration scaffold, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25. Our model, data, and code will be open-source at https://github.com/zhengkid/Parallel-R1.
Community
Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose Parallel-R1, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model’s thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a mid-training exploration scaffold, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25.
done ~ - ~ whitout reading
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
- VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning (2025)
- Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner (2025)
- Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning (2025)
- RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback (2025)
- Train Long, Think Short: Curriculum Learning for Efficient Reasoning (2025)
- Diversity-Enhanced Reasoning for Subjective Questions (2025)
- JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models (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