English

Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric

Computation and Language 2026-03-02 v2

Abstract

Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking in open-ended alignment. We argue that robust alignment for non-verifiable tasks is fundamentally a principle generalization problem: reward should not be a learned function internalized into a judge, but an explicit reasoning process executed under inspectable principles. To operationalize this view, we present the Open Rubric System (OpenRS), a plug-and-play, rubrics-based LLM-as-a-Judge framework built around Pairwise Adaptive Meta-Rubrics (PAMR) and lightweight Pointwise Verifiable Rubrics (PVRs), which provide both hard-constraint guardrails and verifiable reward components when ground-truth or programmatic checks are available. OpenRS uses an explicit meta-rubric -- a constitution-like specification that governs how rubrics are instantiated, weighted, and enforced -- and instantiates adaptive rubrics on the fly by conditioning on the semantic differences between two candidate responses. It then performs criterion-wise pairwise comparisons and aggregates criterion-level preferences externally, avoiding pointwise weighted scalarization while improving discriminability in open-ended settings. To keep principles consistent yet editable across various domains, we introduce a two-level meta-rubric refinement pipeline (automated evolutionary refinement for general principles and a reproducible human-in-the-loop procedure for domain principles), complemented with pointwise verifiable rubrics that act as both guardrails against degenerate behaviors and a source of verifiable reward for objective sub-tasks. Finally, we instantiate OpenRS as reward supervision in pairwise RL training.

Keywords

Cite

@article{arxiv.2602.14069,
  title  = {Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric},
  author = {Ruipeng Jia and Yunyi Yang and Yuxin Wu and Yongbo Gai and Siyuan Tao and Mengyu Zhou and Jianhe Lin and Xiaoxi Jiang and Guanjun Jiang},
  journal= {arXiv preprint arXiv:2602.14069},
  year   = {2026}
}
R2 v1 2026-07-01T10:37:24.637Z