Rubric-Grounded RL: Structured Judge Rewards for Generalizable Reasoning

• URL: http://arxiv.org/abs/2605.08061v1
• Date: Fri, 08 May 2026 17:48:58 GMT
• Title: Rubric-Grounded RL: Structured Judge Rewards for Generalizable Reasoning
• Abstract summary: We formalize emphrubric-grounded reinforcement learning (RL): a framework in which the policy is optimized against a structured, multi-criterion reward.<n>We instantiate the framework by deriving rubrics from an Office of Scientific and Technical Information (OSTI)-derived corpus of roughly 100,000 scientific and technical documents.
• Score: 1.517713730645682
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We argue that decomposing reward into weighted, verifiable criteria and using an LLM judge to score them provides a partial-credit optimization signal: instead of a binary outcome or a single holistic score, each response is graded along multiple task-specific criteria. We formalize \emph{rubric-grounded reinforcement learning (RL)}: a framework in which the policy is optimized against a structured, multi-criterion reward produced by a frozen LLM judge that conditions on auxiliary grounding the policy never sees. We instantiate the framework by deriving rubrics from an Office of Scientific and Technical Information (OSTI)-derived corpus of roughly 100,000 scientific and technical documents and training Llama-3.1-8B-Instruct with Group Relative Policy Optimization (GRPO). With GRPO-based training, the model achieves $71.7\%$ normalized reward on held-out rubric evaluation. The GRPO-tuned policy also improves over the base model on four reasoning benchmarks not derived from the training corpus -- GSM8K, MATH, GPQA Main, and GPQA Diamond. These results provide evidence that structured, document-grounded rewards can improve held-out rubric performance and induce transferable reasoning behaviors beyond the corpus used to construct the training environment.

Related papers

• On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse [2.5845893156827153]
  Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline.<n>We provide a rigorous derivation of GRPO from first principles of the policy gradient theorem, revealing a fundamental credit assignment failure.<n>Our results characterize when GRPO's simplicity is theoretically justified and identify the credit assignment bottleneck as the key limitation for multi-step reasoning.
  arXiv  Detail & Related papers  (2026-06-28T06:51:45Z)
• VIMPO: Value-Implicit Policy Optimization for LLMs [106.88933849641272]
  Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token.<n>Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability.<n>We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from optimality conditions of KL-regularized reinforcement learning.
  arXiv  Detail & Related papers  (2026-06-18T09:44:12Z)
• QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards [68.15832368034815]
  We present a framework that co-designs queries and rubrics.<n>QUBRIC achieves a +5.5 point gain on ArenaHard over the SFT baseline.
  arXiv  Detail & Related papers  (2026-06-02T17:53:04Z)
• RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains [19.25508787530297]
  RUBRIC-ARROW is an alternating framework that jointly trains a rubric generator and a rubric-conditioned judge, with its RL stage using only pairwise preference data.<n>Our method couples a probability-based scoring rule that reduces ties with phase-specific preference-based rewards and an alternating GRPO scheme that together train the pointwise evaluator.
  arXiv  Detail & Related papers  (2026-05-27T22:46:25Z)
• RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards [76.17893114021757]
  Deep research systems that plan, search, evaluate evidence, and synthesize long-form reports lack ground-truth answers and span many tool-augmented decisions.<n>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.<n>We introduceEM, a rubric-guided reinforcement learning framework that combines stagewise policy decomposition with reflection-based meta-policy evolution.
  arXiv  Detail & Related papers  (2026-05-11T17:40:38Z)
• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation [50.696688705287755]
  We propose Mutual Information Self-Evaluation to overcome the sparse reward challenge in reinforcement learning.<n>MISE enables an agent to learn autonomously from dense internal rewards supplementing sparse extrinsic signals.<n>We prove that utilizing hindsight self-evaluation rewards is equivalent to minimizing an objective that combines mutual information with a KL divergence term between the policy and a proxy reward policy.
  arXiv  Detail & Related papers  (2026-04-13T15:18:51Z)
• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• GOPO: Policy Optimization using Ranked Rewards [12.100854296428524]
  Group Ordinal Policy Optimization (GOPO) uses only the ranking of the rewards and discards their magnitudes.<n>We demonstrate consistent improvements across a range of tasks and model sizes.
  arXiv  Detail & Related papers  (2026-02-01T22:07:11Z)
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains [9.917318870162365]
  Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding.<n>Rubrics have recently been used in evaluation benchmarks to capture such judgments, but their potential as reward signals for on-policy post-training remains underexplored.<n>We introduce RaR, an on-policy reinforcement learning method that extends RLVR beyond verifiable domains by using rubric-based feedback.
  arXiv  Detail & Related papers  (2025-07-23T17:57:55Z)
• GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning.<n>Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate.<n>We propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision.
  arXiv  Detail & Related papers  (2025-06-19T08:49:13Z)
• Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective [6.069069082518759]
  We study the Zero-Reward Assumption in reinforcement learning for large language models (LLMs)<n>We show that the policy gradient based on true, unknown token-level rewards can be unbiasedly estimated using only a response-level reward model.<n>We propose a new algorithm: Token-Reinforced Policy Optimization (TRePO)
  arXiv  Detail & Related papers  (2025-06-03T07:44:31Z)
• Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO [22.00487909203855]
  Group Relative Policy Optimization fails to update a policy when all responses within a group are incorrect.<n>This limitation underscores a key gap between artificial and human intelligence.<n>We introduce a simple framework that mitigates the all-negative-sample issue by incorporating response diversity within groups.
  arXiv  Detail & Related papers  (2025-05-16T18:02:05Z)
• CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models [77.16976971950785]
  This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models.<n>CPPO prunes completions with low absolute advantages, significantly reducing the number needed for gradient calculation and updates.<n> Experiments show that CPPO achieves up to $7.98times$ speedup on GSM8K and $3.48times$ on Math while preserving or even enhancing the accuracy compared to the original GRPO.
  arXiv  Detail & Related papers  (2025-03-28T11:30:05Z)
• Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance [52.65461207786633]
  Policy-based Reinforcement Learning from Human Feedback is essential for aligning large language models with human preferences.<n>It requires joint training of an actor and critic with a pretrained, fixed reward model for guidance.<n>We propose textbfDecoupled Value Policy Optimization (DVPO), a lean framework that replaces traditional reward modeling with a pretrained emphglobal value model (GVM)
  arXiv  Detail & Related papers  (2025-02-24T08:11:33Z)
• Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning [43.123290672073814]
  We deal with systems that generate summaries from document(s) based on a query. Motivated by the insight that Reinforcement Learning (RL) provides a generalization to Supervised Learning (SL) for Natural Language Generation, we use an RL-based approach for this task. We develop multiple Policy Gradient networks, trained on various reward signals: ROUGE, BLEU, and Semantic Similarity.
  arXiv  Detail & Related papers  (2023-11-29T10:38:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.