paper-with-me

홈 › Papers

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning

2025-09-19 · Zhiling Ye, Yun Yue, Haowen Wang, Xudong Han, Jiadi Jiang, Cheng Wei, Lei Fan, Jiaxin Liang, Shuowen Zhang, Ji Li, Chunxiao Guo, Jian Wang, Peng Wei, Jinjie Gu arxiv

Open-ended evaluation is essential for deploying large language models in real-world settings. In studying HealthBench, we observe that using the model itself as a grader and generating rubric-based reward signals substantially improves reasoning performance. Remarkably, the trained model also becomes a stronger grader. Motivated by this, we introduce Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning, a lightweight framework that enables faster and more resource-efficient training while surpassing baselines. Remarkably, on Qwen3-32B, training with just the 4000-sample HealthBench Easy subset is sufficient to obtain a model that exceeds GPT-5 on HealthBench Hard. Incorporating a small amount of teacher-graded data further enhances performance for less capable models.

📄 PDF Abstract BibTeX arXiv:2509.25534

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics

2026-02-11 · Leheng Sheng, Wenchang Ma, Ruixin Hong, Xiang Wang 외 arxiv

Despite chain-of-thought (CoT) playing crucial roles in LLM reasoning, directly rewarding it is difficult: training a reward model demands heavy human labeling efforts, and static RMs struggle with evolving CoT distribut…

ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning

2026-05-22 · Xiaoyuan Li, Keqin Bao, Moxin Li, Yubo Ma 외 arxiv

Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existin…

Reinforcement LearningContinual PretrainingInstruction Following

SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning

2026-07-29 · Jianze Wang, Kunwang Zheng, Ying Liu, Yu Cao 외 arxiv

Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback. Existing methods rely on answer voting and therefore do not extend naturally to open-ended genera…

Reinforcement Learning

EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning

2026-06-22 · Hongxin Ding, Baixiang Huang, Yue Fang, Weibin Liao 외 arxiv

Rubric-based rewards offer interpretable and fine-grained optimization signals for reinforcement learning in open-ended tasks where verifiable answers are unavailable. However, pre-constructed rubrics remain static throu…

Reinforcement Learning

Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance

2026-05-08 · Jiachen Yu, Zhihao Xu, Junjie Wang, Yujiu Yang arxiv

Rubrics have been extensively utilized for evaluating unverifiable, open-ended tasks, with recent research incorporating them into reward systems for reinforcement learning. However, existing frameworks typically treat r…

Reinforcement LearningInstruction Following