method · first seen 4 Oct 2026
rubric-based reward
Also: RL with rubrics, rubric-based RL, rubric generation, rubric-based judging, rubric-based scoring, rubric-based reinforcement learning
Reinforcement learning rewards derived from scoring responses against multiple written criteria.
Mentions per week
PapersCodeDiscussion
Earliest sources
- RubricArmor: Adversarial Evolution Improves LLM-Based Rubric GenerationPapers · 4 Oct 2026 · Haocheng Yang, Yuchao Zhang, Licheng Pan, Jiajun Fan, Maolin Wang, Kangning Zhan…
- VERA: Scaling Verifiable Environments for Agentic co-EvolutionPapers · 5 Oct 2026 · Junqi Liu, Yongyang Pan, Zhuosong Jiang, Dongbai Li, Bo Zhang, Xitong Ling, Shen…
- Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer ScoringPapers · 7 Oct 2026 · Zhifan Sun, Sebastian Gombert, Fabian Zehner, Leon Camus, Longwei Cong, Hendrik…
- Alice: A Large-Scale German Benchmark for Rubric-Based Multi-Dimensional Automatic Short Answer ScoringPapers · 7 Oct 2026 · Zhifan Sun, Sebastian Gombert, Jannik Lossjew, Tobias Wyrwich, Berrit Katharina…
- RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement LearningPapers · 13 Oct 2026 · Kunwang Zheng, Xinyu Sun, Yu Cao, Shuocheng Li, Lei Cheng, Ying Liu, Qilong Zhan…
- CoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement LearningPapers · 13 Oct 2026 · Guangcheng Zhu, Yingfan Ma, Xing Zheng, Haobo Wang, Shenzhi Yang, Kai Tang, Zhen…
Latest sources
- RuACT: Recovering Inactive Rubrics as Adaptive Critics and TeachersPapers · 6 Nov 2026 · Yijun Li, Zhengxi Lu, Zhipiao Liu, Jinzheng Yu, Xutao Weng, Jian Shao, Yongliang…
- Agent-R$^2$: Scaling Agents for Realistic Productivity Work via Real-Source Data SynthesisPapers · 5 Nov 2026 · Teng Pan, Zixuan Wang, Yuchen Yan, Qifei Wu, Yao Chen, Yingqi Qu, Ruiqing Zhang,…
- Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable DomainsPapers · 4 Nov 2026 · Sumeet Ramesh Motwani, Tejas Krishnan, Alistair Letcher, Charles London, Suhaas…
- Reward-Adaptive Co-Evolution of Policy and RubricPapers · 29 Oct 2026 · Yizhu Chen, Jianguang Jiang, Jiameng Huang, Chuyu Fang, Bojun Zhang, Zhenyu Jiao…
- Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended GenerationPapers · 28 Oct 2026 · Chengsheng Zhang, Wenshen Xu, Yuchuan Wu, Zhiyuan Yu, Junfeng Fang, Tianlong Wan…
- Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and TrainingPapers · 28 Oct 2026 · Ulyana Tkachenko, Hui Wen Goh, Guram Gogia, Jonas Mueller
- SetGRPO: Calibrating Grader-Induced Policy OptimizationPapers · 27 Oct 2026 · Jiale Huang, Zixu Li, Zhiwei Chen, Zhiheng Fu, Jinhe Bi, Yupeng Hu
- Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RLPapers · 24 Oct 2026 · Hyun Ryu, Jong-Heon Kim, Yiqing Xie, Seungone Kim, Carolyn Rose, Eunho Yang
- Intra-Rubric Reward Divergence: Mitigating Rubric Hacking through Latent Dimension Recovery and BalancingPapers · 19 Oct 2026 · Jianqiang Xia, Han Xu, Dianxi Shi
- HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RLPapers · 19 Oct 2026 · Xiaoqiang Wang, Ting-En Lin, Yuchuan Wu, Pinyi Zhang, Caixin Kang, Ling Li, Bing…
- Rubrics Beyond Evaluation: Exploiting Rubric Structure in Reinforcement LearningPapers · 19 Oct 2026 · Yuxun Huang, Yunyao Zhang, ZeLiang Chen, Yi-Ping Phoebe Chen, Junqing Yu, Zikai…
- RARE: Reinforcement Learning with Adaptive Rubric Evolution for Open-Ended GenerationPapers · 18 Oct 2026 · Xueyun Tian, Bingbing Xu, Chuyue Li, Jiaming Liu, Chao Zhang, Weijia Feng, MingH…