Elamur Research⌕
☰
home / papers / 2026 / AgentV-RL: Scaling Reward Modeling with Agentic Verifier

AgentV-RL: Scaling Reward Modeling with Agentic Verifier

Paper · 2026 · Jiazheng Zhang, Ziche Fu, Zhiheng Xi et al.

Summary

Verifiers, or reward models, steer test-time scaling (TTS) in LLM reasoning, but they often fail on hard mathematical problems. Single-pass generative judges tend to accept flawed solutions that look plausible, and they make arithmetic or factual mistakes because they have no access to external tools. The authors recast verification as an agentic, multi-turn process called Agentic Verifier. It uses two cooperating roles. A forward agent follows a solution from its premises to its conclusion, checking sufficiency. A backward agent works from the conclusion back to the problem's constraints, checking necessity. Both roles can split solutions into sub-steps and run code to test calculations.

To make the approach practical, AgentV-RL compresses this multi-agent behaviour into one model. It relies on a synthetic engine that generates and filters verification trajectories, followed by rejection-sampling fine-tuning and then reinforcement learning. The verifier improves results in both Best-of-N selection and iterative critique-and-refine loops. The 4B model beats much larger outcome reward models, which points toward tool-grounded agentic reward modeling.

Key points

  • The 4B Agentic Verifier outperforms state-of-the-art ORMs by up to 25.2%. It consistently beats INF-ORM-Llama3.1-70B, a model with about ten times more parameters.
  • Every training stage contributes:
    • The train-free variant already gains up to 2.6 points over the base model on Gaokao2023.
    • SFT on the synthetic data adds further gains.
    • RL adds more on top of SFT.
  • Scaling helps in two ways. Within the Qwen3 series, moving from 0.6B to 1.7B adds 5.2 points on Gaokao2023, and 4B gains further. Sampling more verification trajectories also raises Best-of-N accuracy.
  • The method generalizes beyond mathematics. Agentic-Verifier-Qwen3-4B scores 70.86 on LiveCodeBench and 66.00 on HotpotQA, beating DS-Distill-14B and Mistral-Small-24B-Instruct.
  • Verification costs considerably more than the base model. On one A100 with vLLM at batch size 128, the full verifier averages about 8.3K tokens, 11.3 rounds, 1.6 tool calls and 323 s, versus about 2.6K tokens and 119 s for the base model. Forward-only and backward-only variants offer cheaper trade-offs.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Fudan UniversityShanghai · China202 works · 22,509 citations🎓University of Hong KongPok Fu Lam · China118 works · 13,496 citations🏢ByteDanceBeijing · China47 works · 4,339 citations🎓Huazhong University of Science and TechnologyWuhan · China59 works · 8,310 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang and Xuanjing Huang. 2026. AgentV-RL: Scaling Reward Modeling with Agentic Verifier. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1156

@inproceedings{zhang2026agentv,
  title = {{AgentV-RL: Scaling Reward Modeling with Agentic Verifier}},
  author = {Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang and Xuanjing Huang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1156},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1156}
}

References

61 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Chenxin An, Zhihui Xie, Xiaonan Li, Lei Li, Jun Zhang, Shansan Gong, Ming Zhong, Jingjing Xu, Xipeng Qiu, Mingxuan Wang, and Lingpeng Kong. 2025. Polaris: A post-training recipe for scaling reinforcement learning on advanced reasoning models. find
  2. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, Xiaoyi Dong, Haodong Duan, Qi Fan, Zhaoye Fei, Yang Gao, Jiaye Ge, Chenya Gu, Yuzhe Gu, Tao Gui, and 81 others. 2024. Internlm2 technical report. Preprint, arXiv:2403.17297.
  3. Luoxin Chen, Jinming Gu, Liankai Huang, Wenhao Huang, Zhicheng Jiang, Allan Jie, Xiaoran Jin, Xing Jin, Chenggang Li, Kaijing Ma, and 1 others. 2025a. Seed-prover: Deep and broad reasoning for automated theorem proving. arXiv preprint arXiv:2507.23726. find
  4. Nuo Chen, Zhiyuan Hu, Qingyun Zou, Jiaying Wu, Qian Wang, Bryan Hooi, and Bingsheng He. 2025b. Judgelrm: Large reasoning models as a judge. arXiv preprint arXiv:2504.00050. — [arXiv:2504.00050](https://arxiv.org/abs/2504.00050) find
  5. Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, and 1 others. 2025c. Better process supervision with bi-directional rewarding signals. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14471–14485. find
  6. Xiusi Chen, Gaotang Li, Ziqi Wang, Bowen Jin, Cheng Qian, Yu Wang, Hongru Wang, Yu Zhang, Denghui Zhang, Tong Zhang, Hanghang Tong, and Heng Ji. 2025d. RM-R1: reward modeling as reasoning. CoRR, abs/2505.02387.
  7. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training verifiers to solve math word problems. CoRR, abs/2110.14168.
  8. Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Yuchen Zhang, Jiacheng Chen, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, Jiarui Yuan, Huayu Chen, Kaiyan Zhang, Xingtai Lv, Shuo Wang, Yuan Yao, Xu Han, and 6 others. 2025. Process reinforcement through implicit rewards. Prepri…
  9. Google DeepMind. 2025. Advanced version of gemini with deep think officially achieves gold-medal standard at the international mathematical olympiad. find
  10. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  11. Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, and Zhicheng Dou. 2025a. Agentic entropy-balanced policy optimization. CoRR, abs/2510.14545. — [arXiv:2510.14545](https://arxiv.org/abs/2510.14545) find
  12. Guanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Yutao Zhu, Hangyu Mao, Guorui Zhou, Zhicheng Dou, and Ji-Rong Wen. 2025b. Tool-star: Empowering llm-brained multi-tool reasoner via reinforcement learning. CoRR, abs/2505.16410. — [arXiv:2505.16410](https://arxiv.org/abs/2505.16410) find
  13. Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. 2025. Retool: Reinforcement learning for strategic tool use in llms. CoRR, abs/2504.11536.
  14. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  15. Lin Gui, Cristina Garbacea, and Victor Veitch. 2024. Bonbon alignment for large language models and the sweetness of best-of-n sampling. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, Dece… find
  16. Honglin Guo, Kai Lv, Qipeng Guo, Tianyi Liang, Zhiheng Xi, Demin Song, Qiuyinzhe Zhang, Yu Sun, Kai Chen, Xipeng Qiu, and 1 others. 2025a. Critiq: Mining data quality criteria from human preferences. arXiv preprint arXiv:2502.19279. find
  17. Jiaxin Guo, Zewen Chi, Li Dong, Qingxiu Dong, Xun Wu, Shaohan Huang, and Furu Wei. 2025b. Reward reasoning model. arXiv preprint arXiv:2505.14674. — [arXiv:2505.14674](https://arxiv.org/abs/2505.14674) find
  18. Jujie He, Tianwen Wei, Rui Yan, Jiacai Liu, Chaojie Wang, Yimeng Gan, Shiwen Tu, Chris Yuhao Liu, Liang Zeng, Xiaokun Wang, Boyang Wang, Yongcong Li, Fuxiang Zhang, Jiacheng Xu, Bo An, Yang Liu, and Yahui Zhou. 2024. Skywork-o1 open series. find
  19. Yichen Huang and Lin F Yang. 2025. Gemini 2.5 pro capable of winning gold at imo 2025. arXiv preprint arXiv:2507.15855, 7:7. — [arXiv:2507.15855](https://arxiv.org/abs/2507.15855) find
  20. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. 2024. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:2403.07974.
  21. Zhewei Kang, Xuandong Zhao, and Dawn Song. 2025. Scalable best-of-n selection for large language models via self-certainty. CoRR, abs/2502.18581. find
  22. Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran, Jaekyeom Kim, Hao Peng, Moontae Lee, Honglak Lee, and Lu Wang. 2026. Process reward models that think. find
  23. Trans. Mach. Learn. Res., 2026. find
  24. Lei Li, Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian, Ningyu Zhang, and Hua Wu. 2024. Tool-augmented reward modeling. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. find
  25. Yi-Chen Li, Tian Xu, Yang Yu, Xuqin Zhang, Xiong-Hui Chen, Zhongxiang Ling, Ningjing Chao, Lei Yuan, and Zhi-Hua Zhou. 2025. Generalist reward models: Found inside large language models. arXiv preprint arXiv:2506.23235. — [arXiv:2506.23235](https://arxiv.org/abs/2506.23235) find
  26. Dakota Mahan, Duy Van Phung, Rafael Rafailov, Chase Blagden, Nathan Lile, Louis Castricato, Jan-Philipp Fränken, Chelsea Finn, and Alon Albalak. 2024b. Generative reward models. arXiv preprint arXiv:2410.12832. find
  27. Zhiyu Mei, Wei Fu, Kaiwei Li, Guangju Wang, Huanchen Zhang, and Yi Wu. 2025. Real: Efficient rlhf training of large language models with parameter reallocation. In Proceedings of the Eighth Conference on Machine Learning and Systems, MLSys 2025, Santa Clara, CA, USA, May 12-15, 2025. mlsys.org. find
  28. Xiaoyu Tan Minghao Yang, Chao Qu. 2024. Inf-orm-llama3.1-70b. find
  29. Minpeng Liao, Chengxi Li, Wei Luo, Jing Wu, and Kai Fan. 2024. MARIO: math reasoning with code interpreter output - A reproducible pipeline. In Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, pages 905–924. Association f…
  30. Mistral AI. 2025. Mistral small 3. find
  31. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Rev…
  32. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel J. Candès, and Tatsunori Hashimoto. 2025b. s1: Simple test-time scaling. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMN…
  33. Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, Jujie He, Jiacai Liu, Chaojie Wang, Rui Yan, Wei Shen, Fuxiang Zhang, Jiacheng Xu, Yang Liu, and Yahui Zhou. 2025a. Skywork-reward-v2: Scaling preference data curation via human-ai synergy. arXiv preprint arXiv:2507.01352.
  34. Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, and Yu Wu. 2025b. Inference-time scaling for generalist reward modeling. CoRR, abs/2504.02495.
  35. Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, and Yu Wu. 2025c. Inference-time scaling for generalist reward modeling. arXiv preprint arXiv:2504.02495.
  36. Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, and Yu Wu. 2025d. Inference-time scaling for generalist reward modeling. CoRR, abs/2504.02495.
  37. Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Erran Li, Raluca Ada Popa, and Ion Stoica. 2025. Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl. Notion Blog. find
  38. Dakota Mahan, Duy Phung, Rafael Rafailov, Chase Blagden, Nathan Lile, Louis Castricato, Jan-Philipp Fränken, Chelsea Finn, and Alon Albalak. 2024a. Generative reward models. CoRR, abs/2410.12832. find
  39. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel J. Candès, and Tatsunori Hashimoto. 2025a. s1: Simple test-time scaling. CoRR, abs/2501.19393.
  40. OpenAI. 2025. Openai achieved gold medal-level performance on the 2025 international mathematical olympiad. find
  41. Hao Peng, Yunjia Qi, Xiaozhi Wang, Zijun Yao, Bin Xu, Lei Hou, and Juanzi Li. 2025. Agentic reward modeling: Integrating human preferences with verifiable correctness signals for reliable reward systems. arXiv preprint arXiv:2502.19328.
  42. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  43. Zhihong Shao, Yuxiang Luo, Chengda Lu, ZZ Ren, Jiewen Hu, Tian Ye, Zhibin Gou, Shirong Ma, and Xiaokang Zhang. 2025. Deepseekmath-v2: Towards self-verifiable mathematical reasoning. arXiv preprint arXiv:2511.22570.
  44. Binghai Wang, Rui Zheng, Lu Chen, Yan Liu, Shihan Dou, Caishuang Huang, Wei Shen, Senjie Jin, Enyu Zhou, Chenyu Shi, and 1 others. 2024a. Secrets of rlhf in large language models part ii: Reward modeling. arXiv preprint arXiv:2401.06080.
  45. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024b. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  46. Zhiheng Xi, Dingwen Yang, Jixuan Huang, Jiafu Tang, Guanyu Li, Yiwen Ding, Wei He, Boyang Hong, Shihan Dou, Wenyu Zhan, Xiao Wang, Rui Zheng, Tao Ji, Xiaowei Shi, Yitao Zhai, Rongxiang Weng, Jingang Wang, Xunliang Cai, Tao Gui, and 5 others. 2024a. Enhancing LLM reasoning via critique models with te… — [arXiv:2411.16579](https://arxiv.org/abs/2411.16579) find
  47. Zhiheng Xi, Dingwen Yang, Jixuan Huang, Jiafu Tang, Guanyu Li, Yiwen Ding, Wei He, Boyang Hong, Shihan Dou, Wenyu Zhan, Xiao Wang, Rui Zheng, Tao Ji, Xiaowei Shi, Yitao Zhai, Rongxiang Weng, Jingang Wang, Xunliang Cai, Tao Gui, and 5 others. 2024b. Enhancing LLM reasoning via critique models with te… — [arXiv:2411.16579](https://arxiv.org/abs/2411.16579) find
  48. Ran Xu, Jingjing Chen, Jiayu Ye, Yu Wu, Jun Yan, Carl Yang, and Hongkun Yu. 2025. Incentivizing agentic reasoning in llm judges via tool-integrated reinforcement learning. arXiv preprint arXiv:2510.23038. — [arXiv:2510.23038](https://arxiv.org/abs/2510.23038) find
  49. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 40 others. 2025a. Qwen3 technical report. CoRR, abs/2505.09388.
  50. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025b. Qwen3 technical report. Preprint, arXiv:2505.09388.
  51. Rui Yang, Ruomeng Ding, Yong Lin, Huan Zhang, and Tong Zhang. 2024. Regularizing hidden states enables learning generalizable reward model for llms. arXiv preprint arXiv:2406.10216. — [arXiv:2406.10216](https://arxiv.org/abs/2406.10216) find
  52. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 conference on empirical methods in natural language processing, pages 2369–…
  53. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiant… — DAPO: An Open-Source LLM Reinforcement Learning System at Scale
  54. Lifan Yuan, Wendi Li, Huayu Chen, Ning Ding, Kaiyan Zhang, Bowen Zhou, Zhiyuan Liu, and Hao Peng. 2025. Free process rewards without process labels. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net.
  55. Jiazheng Zhang, Wenqing Jing, Zizhuo Zhang, Zhiheng Xi, Shihan Dou, Rongxiang Weng, Jiahuan Li, Jingang Wang, Mingxu Chai, Shibo Hong, Tao Gui, and Qi Zhang. 2025a. Two minds better than one: Collaborative reward modeling for LLM alignment. CoRR, abs/2505.10597. — [arXiv:2505.10597](https://arxiv.org/abs/2505.10597) find
  56. Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2024. Generative verifiers: Reward modeling as next-token prediction. arXiv preprint arXiv:2408.15240.
  57. Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2025b. Generative verifiers: Reward modeling as next-token prediction. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net.
  58. Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025c. The lessons of developing process reward models in mathematical reasoning. arXiv preprint arXiv:2501.07301.
  59. Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025d. The lessons of developing process reward models in mathematical reasoning. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27…
  60. Jialun Zhong, Wei Shen, Yanzeng Li, Songyang Gao, Hua Lu, Yicheng Chen, Yang Zhang, Wei Zhou, Jinjie Gu, and Lei Zou. 2025. A comprehensive survey of reward models: Taxonomy, applications, challenges, and future. arXiv preprint arXiv:2504.12328. — [arXiv:2504.12328](https://arxiv.org/abs/2504.12328) find
  61. Banghua Zhu, Evan Frick, Tianhao Wu, Hanlin Zhu, and Jiantao Jiao. 2023. Starling-7b: Improving llm helpfulness & harmlessness with rlaif. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-agentv-rl-scaling-reward-modeling/