paper-with-me

Papers

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

2026-05-11 · Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan, Yanfei Chen, Chun-Liang Li, Long T. Le, Rujun Han, George Lee, Hanghang Tong, Chen-Yu Lee, Tomas Pfister 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 answers, their trajectories span many tool-augmented decisions, and standard post-training offers little mechanism for turning past attempts into reusable experience. In this work, we argue that rubrics should serve not merely as final-answer evaluators, but as the shared interface that structures policy execution, judge feedback, and agent memory. Based on this view, we introduce RubricEM, a rubric-guided reinforcement learning framework that combines stagewise policy decomposition with reflection-based meta-policy evolution. RubricEM first makes research trajectories stage-aware by conditioning planning, evidence gathering, review, and synthesis on self-generated rubrics. It then assigns credit with Stage-Structured GRPO, which uses stagewise rubric judgments to provide denser semantic feedback for long-horizon optimization. In parallel, RubricEM trains a shared-backbone reflection meta-policy that distills judged trajectories into reusable rubric-grounded guidance for future attempts. The resulting RubricEM-8B achieves strong performance across four long-form research benchmarks, outperforming comparable open models and approaching proprietary deep-research systems. Beyond final performance, we perform thorough analyses to understand the key ingredients of RubricEM.

📄 PDF Abstract BibTeX arXiv:2605.10899

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification

2026-01-22 · Yuxuan Wan, Tianqing Fang, Zaitang Li, Yintong Huo 외 arxiv

Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving. While the majority of existing efforts focus on enhancing policy capabilities via post-training, we propo…

Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers

2026-06-10 · MohammadHossein Rezaei, Anas Mahmoud, Zihao Wang, Utkarsh Tyagi 외 arxiv

Rubrics have emerged as an alternative to RLVR in open-ended domains where a single ground-truth final answer is not available. Existing rubric-based training methods rely on an LLM verifier that scores each rollout agai…

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

EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation

2026-05-28 · Xin Guan, Xiaomeng Hu, Shen Huang, Zhenyi Wang 외 arxiv

Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive reward…

Reinforcement LearningResponse Generation

Co-Evolving LLM Evaluators and Policies via DynamicRubric

2026-07-22 · Beining Wang, Weihang Su, Hongtao Tian, Hao Kong 외 arxiv

Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models. As policies improve, these sampled responses become close in quality. These close candidate…