EvoRubrics introduces adversarial co-evolution between policy LLM and rubric generator to produce dynamic, adaptive rewards for reinforcement learning on open-ended tasks.
hub
Online rubrics elicitation from pairwise comparisons
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 14roles
background 3polarities
background 3representative citing papers
RGSD distills rubric-conditioned teacher distributions into base policies token-by-token, matching GRPO rubric satisfaction on Qwen models with one rollout and zero verifier calls.
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.
ARL-RR alternates optimization over rubric meta-classes with dynamic selection to avoid fixed scalarization, outperforming baselines on HealthBench.
ARCO co-trains an LLM agent with a per-step rubric model whose natural-language criteria and scoring function evolve with the policy, and reports the best exact-match accuracy in all six benchmark/backbone settings compared.
Reasoning Arena converts non-diverse reward groups in RLVR into relative rewards via adaptive trace tournaments and Bradley-Terry fitting on anchor comparisons, claiming 7.6% average gains and 27-41% faster training on math/coding benchmarks.
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.
RUBRIC-ARROW is an alternating rubric generator and judge framework that uses probability-based scoring and pairwise preferences to improve pointwise reward modeling accuracy for LLM post-training in non-verifiable domains.
GrowLoop proposes a human-seeded self-evolving framework that co-evolves rubrics and cases to evaluate conversational human-likeness with differentiated agreement rules.
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.
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.
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.
RIFT taxonomy identifies eight failure modes in rubric design for LLMs and provides automated metrics matching human judgments with up to 0.925 F1 score.
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.
citing papers explorer
-
EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
EvoRubrics introduces adversarial co-evolution between policy LLM and rubric generator to produce dynamic, adaptive rewards for reinforcement learning on open-ended tasks.
-
Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers
RGSD distills rubric-conditioned teacher distributions into base policies token-by-token, matching GRPO rubric satisfaction on Qwen models with one rollout and zero verifier calls.
-
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.
-
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.
-
ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents
ARCO co-trains an LLM agent with a per-step rubric model whose natural-language criteria and scoring function evolve with the policy, and reports the best exact-match accuracy in all six benchmark/backbone settings compared.
-
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
Reasoning Arena converts non-diverse reward groups in RLVR into relative rewards via adaptive trace tournaments and Bradley-Terry fitting on anchor comparisons, claiming 7.6% average gains and 27-41% faster training on math/coding benchmarks.
-
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.
-
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
RUBRIC-ARROW is an alternating rubric generator and judge framework that uses probability-based scoring and pairwise preferences to improve pointwise reward modeling accuracy for LLM post-training in non-verifiable domains.
-
GrowLoop: Self-Evolving Conversation Evaluation Seeded by Human
GrowLoop proposes a human-seeded self-evolving framework that co-evolves rubrics and cases to evaluate conversational human-likeness with differentiated agreement rules.
-
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.
-
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.
-
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.
-
RIFT: A RubrIc Failure Mode Taxonomy and Automated Diagnostics
RIFT taxonomy identifies eight failure modes in rubric design for LLMs and provides automated metrics matching human judgments with up to 0.925 F1 score.
-
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.