paper-with-me

홈 › Papers

Deep Research as Rubric for Reinforcement Learning

2026-05-31 · Wangyi Mei, Zhouhong Gu, Zhenhan Bai, Yin Cai, Lefan Zhang, Zhenxin Ding, Bo Chen, Yan Gao, Yi Wu, Yao Hu, Jiaqing Liang, Deqing Yang arxiv

Open-ended reasoning and long-form generation tasks lack reliable automatic verification signals for reward-based policy optimization. Rubrics offer a promising alternative, but existing approaches treat them as given artifacts -- either hand-crafted or prompt-generated -- and often miss the task-specific, knowledge-intensive dimensions that matter most, distorting the reward signal. Our key observation is that rubric construction is itself a research problem: identifying what makes a response correct or insightful requires discovering and synthesizing external knowledge. We propose Deep Research as Rubric (DR-rubric), a two-stage framework for constructing such rubrics. Stage I elicits domain facts, structural constraints, and failure modes through iterative multi-turn agentic search; Stage II distills this evidence into atomic, independently verifiable constraints for GRPO-based policy optimization. Because the model under training can serve as its own rubric generator, DR-rubric-8B supports bootstrap rubric generation without frontier-model assistance. We evaluate on 6 benchmarks spanning agentic research and expert reasoning. Experiments show that DR-Rubric achieves strong competitive performance with only 1K -- 3K training instances, where GPT-5-generated rubrics particularly benefit breadth coverage on agentic tasks, Gemini-generated rubrics yield the most balanced performance across agentic and expert reasoning tasks, and bootstrap rubrics exhibit a specialization-to-rebalancing evolution achieving the best overall performance at the third iteration. Results demonstrate that reframing rubric construction from static evaluation templates into an evidence-driven research process yields more scalable, fine-grained reward signals for open-ended tasks.

📄 PDF Abstract BibTeX arXiv:2606.01091

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

2026-05-11 · Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan 외 arxiv

Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the regime of verifiable rewards. Their outputs lack ground-truth…

Reinforcement Learning

DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

2026-06-15 · Minghang Zhu, Chuyang Wei, Junhao Xu, Yilin Cheng 외 arxiv

Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria t…

Reinforcement Learning

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

2025-11-24 · Rulin Shao, Akari Asai, Shannon Zejiang Shen, Hamish Ivison 외 arxiv

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with…

Reinforcement LearningFact Checking

Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation

2026-02-03 · Changze Lv, Jie Zhou, Wentao Zhao, Jingwen Xu 외 arxiv

Nowadays, developing reliable DeepResearch-style long-form report generation remains challenging, as training and evaluation lack verifiable reward signals. Accordingly, rubric-based evaluation has become a common practi…

Reinforcement Learning

A Survey on Rubric-Guided Reinforcement Learning for Language Models

2026-08-27 · Zifei Shan, Fangning Shao arxiv

Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models (LLMs) with human preferences. However, traditional RLHF relies on scalar reward signals that lack int…

Reinforcement Learning