paper-with-me

Papers

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

2025-05-30 · Mingjie Liu, Shizhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, Yi Dong

Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's reasoning capabilities or merely amplifies high-reward outputs already latent in the base model's distribution, and whether continually scaling up RL compute reliably leads to improved reasoning performance. In this work, we challenge prevailing assumptions by demonstrating that prolonged RL (ProRL) training can uncover novel reasoning strategies that are inaccessible to base models, even under extensive sampling. We introduce ProRL, a novel training methodology that incorporates KL divergence control, reference policy resetting, and a diverse suite of tasks. Our empirical analysis reveals that RL-trained models consistently outperform base models across a wide range of pass@k evaluations, including scenarios where base models fail entirely regardless of the number of attempts. We further show that reasoning boundary improvements correlates strongly with task competence of base model and training duration, suggesting that RL can explore and populate new regions of solution space over time. These findings offer new insights into the conditions under which RL meaningfully expands reasoning boundaries in language models and establish a foundation for future work on long-horizon RL for reasoning. We release model weights to support further research: https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B

📄 PDF Abstract BibTeX arXiv:2505.24864

Code (1)

open-thought/reasoning-gym 공식 구현

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework

2026-05-18 · Chengpeng Hu, Yingqian Zhang, Hendrik Baier arxiv

Deep reinforcement learning (DRL) has recently emerged as a promising approach to solve combinatorial optimization problems such as job shop scheduling. However, the policies learned by DRL are typically represented by d…

Reinforcement Learning

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

2026-03-19 · Hao Zhang, Mingjie Liu, Shaokun Zhang, Songyang Han 외 arxiv

Multi-turn LLM agents are increasingly important for solving complex, interactive tasks, and reinforcement learning (RL) is a key ingredient for improving their long-horizon behavior. However, RL training requires genera…

Reinforcement Learning

BroRL: Scaling Reinforcement Learning via Broadened Exploration

2025-10-01 · Jian Hu, Mingjie Liu, Ximing Lu, Fang Wu 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key ingredient for unlocking complex reasoning capabilities in large language models. Recent work ProRL has shown promise in scaling RL by increasing…

Reinforcement Learning

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

2026-05-27 · Hongru Hou, Tiehua Mei, Denghui Geng, Jinhui Huang 외 arxiv

Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provides a principled framework for optimizing …

Reinforcement Learning

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View

2025-10-05 · Xinhao Yao, Lu Yu, Xiaolin Hu, Fengwei Teng 외 arxiv

The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved. Some studies contend that RLVR mainly …

Reinforcement Learning