paper-with-me

Papers

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

2025-11-24 · Rulin Shao, Akari Asai, Shannon Zejiang Shen, Hamish Ivison, Varsha Kishore, Jingming Zhuo, Xinran Zhao, Molly Park, Samuel G. Finlayson, David Sontag, Tyler Murray, Sewon Min, Pradeep Dasigi, Luca Soldaini, Faeze Brahman, Wen-tau Yih, Tongshuang Wu, Luke Zettlemoyer, Yoon Kim, Hannaneh Hajishirzi, Pang Wei Koh 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 verifiable rewards, which does not extend to realistic long-form tasks. We address this with Reinforcement Learning with Evolving Rubrics (RLER), where rubrics are constructed and maintained to co-evolve with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop Deep Research Tulu (DR Tulu-8B), the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).

📄 PDF Abstract BibTeX arXiv:2511.19399

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningFact Checking

Similar Papers 제목 키워드 기반

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

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning

2026-08-03 · Fangxu Yu, Tao Feng, Dehai Min, Zinan Lin 외 hf

Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs are complementary in their limitations: …

Reinforcement Learning

BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics

2026-08-17 · Junqi Liu, Yufan He, Yexiao He, Pengfei Guo 외 arxiv

Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi-stage and data-sensitive, while expert trajectories remain scarce a…

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

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