Co-ReAct adds step-level rubric guidance to ReAct agents via a GRPO-trained generator using list-wise ranking rewards, yielding consistent gains on DeepResearchBench and SQA-CS-V2.
hub Canonical reference
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
Canonical reference. 91% of citing Pith papers cite this work as background.
46
Pith papers citing it
Background
91% of classified citations
abstract
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation depends on nuanced, multi-criteria judgments rather than binary correctness. Instance-specific 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. We introduce $\textbf{Rubrics as Rewards}$ (RaR), an on-policy reinforcement learning method that extends RLVR beyond verifiable domains by using rubric-based feedback. Across both medical and science domains, we evaluate multiple strategies for aggregating rubric feedback into rewards. The best RaR variant achieves relative improvements of up to $31\%$ on HealthBench and $7\%$ on GPQA-Diamond over popular LLM-as-judge baselines that rely on direct Likert-based rewards. These results demonstrate that RaR-trained policies adapt well to diverse evaluation formats, performing strongly on both rubric-based and multiple-choice tasks. Moreover, we find that using rubrics as structured reward signals yields better alignment for smaller judges and reduces performance variance across judge scales.
hub tools
citation-role summary
background 10
method 1
citation-polarity summary
representative citing papers
AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
Think-with-Rubrics has LLMs generate rubrics internally before responding, outperforming external rubric-as-reward baselines by 3.87 points on average across benchmarks.
Rubric-based on-policy distillation allows training student models using only teacher responses by generating scoring rubrics from contrasts and using them for on-policy optimization, achieving superior performance and up to 10x better sample efficiency than logit-based approaches.
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
Rubric-based LLM judges show self-preference bias, incorrectly marking their own failed outputs as satisfied up to 50% more often on verifiable benchmarks and skewing scores by 10 points on subjective ones.
A rubric-based generative reward model improves reinforced fine-tuning of SWE agents by supplying richer behavioral guidance than binary terminal rewards alone.
ARL-RR alternates optimization over rubric meta-classes with dynamic selection to avoid fixed scalarization, outperforming baselines on HealthBench.
DeepVerifier enables self-evolving deep research agents via rubric-guided verification at test time, delivering 8-11% accuracy gains on GAIA and XBench-DeepSearch subsets.
DR-rubric is a two-stage framework using iterative agentic search to generate atomic verifiable constraints for GRPO-based RL, achieving competitive performance on 6 benchmarks with 1K-3K examples via bootstrap or frontier-model rubrics.
PPC adds a preplan stage to the question-plan-CoT paradigm, achieving best results on 39 of 40 metrics across five math benchmarks with no added inference tokens.
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.
SRaR attributes rubric items to specific steps via an LLM judge, normalizes per-step scores across rollouts, and combines them with outcome rewards via a decoupled advantage estimator, yielding 3.57-point accuracy gains on Qwen3-8B across math benchmarks.
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
Rubric-based RL verifiers can be gamed via partial criterion satisfaction and implicit-to-explicit tricks, yielding proxy gains that do not improve quality under rubric-free judges; stronger verifiers reduce but do not eliminate the mismatch.
SAGE trains a rubric-based verifier and an RL-optimized generator on seed human data to scalably augment LLM knowledge benchmarks, matching human-annotated quality on HellaSwag at lower cost and generalizing to MMLU.
CLR-voyance reformulates inpatient reasoning as POMDP with clinician-validated outcome rubrics, yielding an 8B model that outperforms larger frontier models on the authors' new benchmark.
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
Rubric-grounded RL with LLM judges on document-derived criteria raises Llama-3.1-8B normalized reward to 71.7% on held-out rubrics and improves performance on GSM8K, MATH, and GPQA benchmarks.
SHARP is a neuro-symbolic method that evolves bounded, auditable rule rubrics for LLM trading agents via cross-sample attribution and walk-forward validation, raising compact-model performance by 10-20 percentage points across equity sectors.
RVPO penalizes variance across multiple reward signals during RLHF advantage aggregation, using a LogSumExp operator as a smooth variance penalty to reduce constraint neglect in LLM alignment.
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
citing papers explorer
-
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
Co-ReAct adds step-level rubric guidance to ReAct agents via a GRPO-trained generator using list-wise ranking rewards, yielding consistent gains on DeepResearchBench and SQA-CS-V2.
-
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
-
RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
-
Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
Think-with-Rubrics has LLMs generate rubrics internally before responding, outperforming external rubric-as-reward baselines by 3.87 points on average across benchmarks.
-
Rubric-based On-policy Distillation
Rubric-based on-policy distillation allows training student models using only teacher responses by generating scoring rubrics from contrasts and using them for on-policy optimization, achieving superior performance and up to 10x better sample efficiency than logit-based approaches.
-
Visual Preference Optimization with Rubric Rewards
rDPO uses offline-built rubrics to generate on-policy preference data for DPO, raising benchmark scores in visual tasks over outcome-based filtering and style baselines.
-
Self-Preference Bias in Rubric-Based Evaluation of Large Language Models
Rubric-based LLM judges show self-preference bias, incorrectly marking their own failed outputs as satisfied up to 50% more often on verifiable benchmarks and skewing scores by 10 points on subjective ones.
-
Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
A rubric-based generative reward model improves reinforced fine-tuning of SWE agents by supplying richer behavioral guidance than binary terminal rewards alone.
-
Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy
ARL-RR alternates optimization over rubric meta-classes with dynamic selection to avoid fixed scalarization, outperforming baselines on HealthBench.
-
Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
DeepVerifier enables self-evolving deep research agents via rubric-guided verification at test time, delivering 8-11% accuracy gains on GAIA and XBench-DeepSearch subsets.
-
Deep Research as Rubric for Reinforcement Learning
DR-rubric is a two-stage framework using iterative agentic search to generate atomic verifiable constraints for GRPO-based RL, achieving competitive performance on 6 benchmarks with 1K-3K examples via bootstrap or frontier-model rubrics.
-
Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning
PPC adds a preplan stage to the question-plan-CoT paradigm, achieving best results on 39 of 40 metrics across five math benchmarks with no added inference tokens.
-
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.
-
Step-wise Rubric Rewards for LLM Reasoning
SRaR attributes rubric items to specific steps via an LLM judge, normalizes per-step scores across rollouts, and combines them with outcome rewards via a decoupled advantage estimator, yielding 3.57-point accuracy gains on Qwen3-8B across math benchmarks.
-
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
-
Revisiting DAgger in the Era of LLM-Agents
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
-
Reward Hacking in Rubric-Based Reinforcement Learning
Rubric-based RL verifiers can be gamed via partial criterion satisfaction and implicit-to-explicit tricks, yielding proxy gains that do not improve quality under rubric-free judges; stronger verifiers reduce but do not eliminate the mismatch.
-
SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
SAGE trains a rubric-based verifier and an RL-optimized generator on seed human data to scalably augment LLM knowledge benchmarks, matching human-annotated quality on HellaSwag at lower cost and generalizing to MMLU.
-
CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics
CLR-voyance reformulates inpatient reasoning as POMDP with clinician-validated outcome rubrics, yielding an 8B model that outperforms larger frontier models on the authors' new benchmark.
-
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
-
Rubric-Grounded RL: Structured Judge Rewards for Generalizable Reasoning
Rubric-grounded RL with LLM judges on document-derived criteria raises Llama-3.1-8B normalized reward to 71.7% on held-out rubrics and improves performance on GSM8K, MATH, and GPQA benchmarks.
-
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents
SHARP is a neuro-symbolic method that evolves bounded, auditable rule rubrics for LLM trading agents via cross-sample attribution and walk-forward validation, raising compact-model performance by 10-20 percentage points across equity sectors.
-
RVPO: Risk-Sensitive Alignment via Variance Regularization
RVPO penalizes variance across multiple reward signals during RLHF advantage aggregation, using a LogSumExp operator as a smooth variance penalty to reduce constraint neglect in LLM alignment.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
POP bootstraps post-training signals for open-ended LLM tasks by synthesizing rubrics during self-play on pretraining corpus, yielding performance gains on Qwen-2.5-7B across healthcare QA, creative writing, and instruction following.
-
C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
C2 synthesizes contrastive helpful/misleading rubric pairs from binary preferences to train cooperative generators and critical verifiers, yielding up to 6.5-point gains on RM-Bench and enabling smaller models to match larger rubric-augmented ones.
-
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework
ReflectRM improves generative reward models by adding self-reflection on analysis quality within a unified training setup for response and analysis preferences, yielding accuracy gains and reduced positional bias on benchmarks.
-
Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation
Small LMs reach 77.1% accuracy at comparative forecasting of research idea success on benchmarks after supervised fine-tuning, with RLVR yielding interpretable reasoning at 71.35%.
-
Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
Systematic false positives in verifiers can cause RLVR training to reach suboptimal plateaus or collapse, with outcomes driven by error patterns rather than overall error rate.
-
MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models
MoRI improves LLM scientific ideation by training models via SFT to generate motivations followed by composite RL rewards for entropy-aware information gain and contrastive semantic alignment, leading to higher novelty, rigor, and feasibility than baselines.
-
Specificity-aware reinforcement learning for fine-grained open-world classification
SpeciaRL applies a dynamic verifier-based reward in reinforcement learning to steer reasoning LMMs toward correct and specific predictions on fine-grained open-world image classification tasks.
-
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
PaTaRM converts pairwise preference data into pointwise reward signals via a novel PAR mechanism and task-adaptive rubrics, reporting 8.7% gains on RewardBench/RMBench and 13.6% relative RLHF improvement.
-
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
DeepSearch embeds MCTS into RLVR training with global frontier selection, entropy guidance, and adaptive replay to achieve 62.95% average accuracy on math reasoning benchmarks while using 5.7x fewer GPU hours than extended training.
-
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Parallel inference rollouts aggregated into pseudo-references enable reference-free RL supervision that matches expert-annotated performance on health tasks while using 9x less test-time compute.
-
On the Generalization Gap in Self-Evolving Language Model Reasoning
Closed-loop self-evolution on LLMs improves reasoning on Knights and Knaves tasks but plateaus short of oracle-supervised levels, with multi-turn revision nearly matching it for large models.
-
CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts
CARE-RL combines PA-GRM for task-adaptive rewards on open-ended tasks and DACSP for modulating RL updates using historical capability directions, reporting higher total average scores than baselines on Qwen models.
-
Reinforcement Learning with Robust Rubric Rewards
RLR³ extends RLVR to criterion-level rubric verification via dual execution paths, minimal exposure masking, hierarchical aggregation, and saturation mitigation, delivering 4.7-point gains over base on 15 benchmarks with Qwen3-VL-30B-A3B.
-
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Lens is a 3.8B-parameter text-to-image model that reaches competitive or superior performance to >6B-parameter systems using 19.3% of the training compute of Z-Image through a densely captioned 800M dataset, multi-resolution batching, semantic VAE, strong language encoder, RL fine-tuning, and 4-step
-
Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants
Fine-tuned simulators grounded in real human data produce LLM assistants that win more often against real users than those trained against role-playing simulators.
-
SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering
SCPRM adds prefix conditioning and schema distance to process reward models so that Monte Carlo Tree Search can explore knowledge-graph reasoning paths with both cumulative and future guidance, yielding a 1.18% average Hits@k gain on medical, legal, and CWQ tasks.
-
LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models
LegalDrill uses diagnosis-driven synthesis and self-reflective verification to create high-quality training data that improves small language models' legal reasoning without expert annotations.
-
PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
-
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
SPARD dynamically tunes multi-objective reward weights and data importance in LLM reinforcement learning alignment using a self-paced curriculum driven by reward dynamics and data utility.
-
Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
The paper describes Baichuan-M4, a coordinated medical agent system that reports leading scores across static knowledge, dynamic consultation, long-context memory, retrieval, OCR, and multimodal tasks with a 3.3% hallucination rate.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
- From Context to Skills: Can Language Models Learn from Context Skillfully?