Elamur Research⌕
☰
home / papers / 2026 / From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models

From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models

Paper · 2026 · Jiaxin Zhang, Wendi Cui, Zhuohang Li et al.

Summary

Most uncertainty quantification (UQ) work on LLMs scores an output only after it has been generated. This survey argues that such retrospective scoring does not fit multi-step reasoning, agents or alignment loops. It traces a shift in which uncertainty becomes a live control input that changes what the model does during operation. The authors, mainly from Salesforce AI Research and Vanderbilt, do not run new large-scale experiments. Instead, they organize existing research into a taxonomy with three application areas:

  • Reasoning: choosing between sampled paths, steering steps within a path, and budgeting how much thinking to do.
  • Autonomous agents: deciding when to call tools, seek information, or pass uncertainty forward through a pipeline.
  • RL and reward modeling: building reward models that are robust to reward hacking, and using confidence as an intrinsic reward for self-improvement.

The survey grounds these uses in Bayesian methods and Conformal Prediction and offers practical design patterns. Its contribution is a unified view of how uncertainty can be used, not only measured. This matters for building LLM systems that are dependable in high-stakes settings.

Key points

  • Reasoning path selection: CISC weights self-consistency votes by each path's length-normalized probability, while CER aggregates confidence at key intermediate steps. Within-Question Discrimination (WQD) matters more for choosing paths than global calibration does.
  • Conformal Prediction: black-box methods such as ConU use semantic similarity as the non-conformity score. White-box Conformal Language Modeling builds next-token prediction sets from logits.
  • Benchmarks: existing ones such as UBench and LM-Polygraph test how well uncertainty is estimated, not how useful it is for control. The authors also consider AUROC poorly suited to interactive settings.
  • Open problems: whether the control signal itself is reliable, how uncertainty propagates in multi-agent systems, how to evaluate in a human-centered way, and how to scale Bayesian methods.
  • Limitations: the paper is a conceptual synthesis without comparative experiments. Its design recommendations appear in Appendix C.

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

🎓University of California, DavisDavis · United States28 works · 41,916 citations🎓Vanderbilt UniversityNashville · United States14 works · 1,413 citations🏥Vanderbilt University Medical CenterNashville · United States3 works · 18 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksEvaluation & benchmarks · 1,220 works

Cite

Cite as Jiaxin Zhang, Wendi Cui, Zhuohang Li, Lifu Huang, Bradley A. Malin, Caiming Xiong and Chien-Sheng Wu. 2026. From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models. 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.2064

@inproceedings{zhang2026passive,
  title = {{From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models}},
  author = {Jiaxin Zhang, Wendi Cui, Zhuohang Li, Lifu Huang, Bradley A. Malin, Caiming Xiong and Chien-Sheng Wu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2064},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2064}
}

References

99 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shivam Agarwal, Zimin Zhang, Lifan Yuan, Jiawei Han, and Hao Peng. 2025. The unreasonable effectiveness of entropy minimization in llm reasoning. arXiv preprint arXiv:2505.15134. find
  2. Ohav Barbi, Ori Yoran, and Mor Geva. 2025. Preventing rogue agents improves multi-agent collaboration. arXiv preprint arXiv:2502.05986. find
  3. Mohammad Beigi, Sijia Wang, Ying Shen, Zihao Lin, Adithya Kulkarni, Jianfeng He, Feng Chen, Ming Jin, Jin-Hee Cho, Dawei Zhou, and 1 others. 2024. Rethinking the uncertainty: a critical review and analysis in the era of large language models. arXiv preprint arXiv:2410.20199. — [arXiv:2410.20199](https://arxiv.org/abs/2410.20199) find
  4. Jan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua, and Owain Evans. 2025. Tell me about yourself: Llms are aware of their learned behaviors. In The Thirteenth International Conference on Learning Representations. find
  5. Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora De… — On the Opportunities and Risks of Foundation Models
  6. Lang Cao, Renhong Chen, Yingtian Zou, Chao Peng, Wu Ning, Huacong Xu, Qian Chen, Yuxian Wang, Peishuo Su, Mofan Peng, and 1 others. 2025. Process reward modeling with entropy-driven uncertainty. arXiv preprint arXiv:2503.22233. — [arXiv:2503.22233](https://arxiv.org/abs/2503.22233) find
  7. Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, and 1 others. 2025. Why do multi-agent llm systems fail? arXiv preprint arXiv:2503.13657. find
  8. Guoxin Chen, Minpeng Liao, Chengxi Li, and Kai Fan. 2024. Alphamath almost zero: process supervision without process. Advances in Neural Information Processing Systems, 37:27689–27724.
  9. John Cherian, Isaac Gibbs, and Emmanuel Candes. 2024. Large language model validity via enhanced conformal prediction methods. Advances in Neural Information Processing Systems, 37:114812–114842. find
  10. Ganqu Cui, Yuchen Zhang, Jiacheng Chen, Lifan Yuan, Zhi Wang, Yuxin Zuo, Haozhan Li, Yuchen Fan, Huayu Chen, Weize Chen, and 1 others. 2025. The entropy mechanism of reinforcement learning for reasoning language models. arXiv preprint arXiv:2505.22617. find
  11. Wendi Cui, Zhuohang Li, Damien Lopez, Kamalika Das, Bradley A Malin, Sricharan Kumar, and Jiaxin Zhang. 2024. Divide-conquer-reasoning for consistency evaluation and automatic improvement of large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Process… find
  12. Longchao Da, Xiaoou Liu, Jiaxin Dai, Lu Cheng, Yaqing Wang, and Hua Wei. 2025. Understanding the uncertainty of llm explanations: A perspective based on reasoning topology. arXiv preprint arXiv:2502.17026. — [arXiv:2502.17026](https://arxiv.org/abs/2502.17026) find
  13. Siddartha Devic, Tejas Srinivasan, Jesse Thomason, Willie Neiswanger, and Vatsal Sharan. 2025. From calibration to collaboration: Llm uncertainty quantification should be more human-centered. arXiv preprint arXiv:2506.07461. — [arXiv:2506.07461](https://arxiv.org/abs/2506.07461) find
  14. Jinhao Duan, James Diffenderfer, Sandeep Madireddy, Tianlong Chen, Bhavya Kailkhura, and Kaidi Xu. 2025. Uprop: Investigating the uncertainty propagation of llms in multi-step agentic decision-making. arXiv preprint arXiv:2506.17419. — [arXiv:2506.17419](https://arxiv.org/abs/2506.17419) find
  15. Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, and Yarin Gal. 2024. Detecting hallucinations in large language models using semantic entropy. Nature, 630(8017):625–630. find
  16. Yu Feng, Ben Zhou, Weidong Lin, and Dan Roth. 2025. Bird: A trustworthy bayesian inference framework for large language models. In The Thirteenth International Conference on Learning Representations. find
  17. Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, and Yanghua Xiao. 2025a. Reward shaping to mitigate reward hacking in rlhf. arXiv preprint arXiv:2502.18770. — [arXiv:2502.18770](https://arxiv.org/abs/2502.18770) find
  18. Yichao Fu, Xuewei Wang, Yuandong Tian, and Jiawei Zhao. 2025b. Deep think with confidence. arXiv preprint arXiv:2508.15260. find
  19. Zeyu Gan, Yun Liao, and Yong Liu. 2025. Rethinking external slow-thinking: From snowball errors to probability of correct reasoning. arXiv preprint arXiv:2501.15602. — [arXiv:2501.15602](https://arxiv.org/abs/2501.15602) find
  20. Leon Chlon, Sarah Rashidi, Zein Khamis, and Mar-cAntonio M Awada. 2025. Llms are bayesian, in expectation, not in realization. arXiv preprint arXiv:2507.11768. — [arXiv:2507.11768](https://arxiv.org/abs/2507.11768) find
  21. Xiang Gao, Jiaxin Zhang, Lalla Mouatadid, and Kamalika Das. 2024. Spuq: Perturbation-based uncertainty quantification for large language models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2336–2346. find
  22. Matej Cief, Francesco Tonolini, Nikolaos Aletras, and Gabriella Kazai. 2024. Adaptive uncertainty-aware reinforcement learning from human feedback. find
  23. Zitian Gao, Lynx Chen, Haoming Luo, Joey Zhou, and Bryan Dai. 2025. One-shot entropy minimization. arXiv preprint arXiv:2505.20282. — [arXiv:2505.20282](https://arxiv.org/abs/2505.20282) find
  24. Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, and 1 others. 2023. A survey of uncertainty in deep neural networks. Artificial Intelligence Review, 56(Suppl 1):1513–1589. find
  25. Jiahui Geng, Fengyu Cai, Yuxia Wang, Heinz Koeppl, Preslav Nakov, and Iryna Gurevych. 2024. A survey of confidence estimation and calibration in large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language… find
  26. Jiuzhou Han, Wray Buntine, and Ehsan Shareghi. 2024. Towards uncertainty-aware language agent. In Findings of the Association for Computational Linguistics ACL 2024, pages 6662–6685. vision? Advances in neural information processing systems, 30. find
  27. Michael Kirchhof, Gjergji Kasneci, and Enkelejda Kasneci. 2025. Position: Uncertainty quantification needs reassessment for large language model agents. In Forty-second International Conference on Machine Learning Position Paper Track. find
  28. Ranganath Krishnan, Piyush Khanna, and Omesh Tickoo. 2024. Enhancing trust in large language models with uncertainty-aware fine-tuning. arXiv preprint arXiv:2412.02904. — [arXiv:2412.02904](https://arxiv.org/abs/2412.02904) find
  29. Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation. In The Eleventh International Conference on Learning Representations. find
  30. Somnath Hazra, Pallab Dasgupta, and Soumyajit Dey. 2025. Tackling uncertainties in multi-agent reinforcement learning through integration of agent termination dynamics. In Proceedings of the 24th International Conference on Autonomous Agents and Multi-agent Systems, pages 960–968. find
  31. Nathan Lambert, Valentina Pyatkin, Jacob Morrison, Lester James Validad Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, and 1 others. 2025. Rewardbench: Evaluating reward models for language modeling. In Findings of the Association for Computational Linguis… find
  32. Jinwei Hu, Yi Dong, Shuang Ao, Zhuoyun Li, Boxuan Wang, Lokesh Singh, Guangliang Cheng, Sarvapali D Ramchurn, and Xiaowei Huang. 2025. Position: Towards a responsible llm-empowered multi-agent systems. arXiv preprint arXiv:2502.01714. — [arXiv:2502.01714](https://arxiv.org/abs/2502.01714) find
  33. Jiaqi Li, Yixuan Tang, and Yi Yang. 2025a. Know the unknown: An uncertainty-sensitive method for llm instruction tuning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 2972– 2989. find
  34. Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, and Bryan Hooi. 2024. Uncertainty of thoughts: Uncertainty-aware planning enhances information seeking in large language models. arXiv preprint arXiv:2402.03271. find
  35. Lei Li, Hehuan Liu, Yaxin Zhou, ZhaoYang Gui, Xudong Weng, Yi Yuan, Zheng Wei, and Zang Li. 2025b. Uncertainty-aware iterative preference optimization for enhanced llm reasoning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages… find
  36. Hsiu-Yuan Huang, Yutong Yang, Zhaoxi Zhang, Sanwoo Lee, and Yunfang Wu. 2024. A survey of uncertainty estimation in llms: Theory meets practice. arXiv preprint arXiv:2410.15326. — [arXiv:2410.15326](https://arxiv.org/abs/2410.15326) find
  37. Yuxian Jiang, Yafu Li, Guanxu Chen, Dongrui Liu, Yu Cheng, and Jing Shao. 2025. Rethinking entropy regularization in large reasoning models. arXiv preprint arXiv:2509.25133. — [arXiv:2509.25133](https://arxiv.org/abs/2509.25133) find
  38. Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson, and 1 others. 2022. Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221. find
  39. Ryo Kamoi, Yusen Zhang, Nan Zhang, Jiawei Han, and Rui Zhang. 2024. When can llms actually correct their own mistakes? a critical survey of self-correction of llms. Transactions of the Association for Computational Linguistics, 12:1417–1440.
  40. Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer Yafu Li, Xuyang Hu, Xiaoye Qu, Linjie Li, and Yu Cheng. 2025c. Test-time preference optimization: On-the-fly alignment via iterative textual feedback. In Forty-second International Conference on Ma… find
  41. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let’s verify step by step. In The Twelfth International Conference on Learning Representations.
  42. Hao Liu, Zi-Yi Dou, Yixin Wang, Nanyun Peng, and Yisong Yue. 2024. Uncertainty calibration for tool-using language agents. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16781–16805. find
  43. Jingyu Liu, JingquanPeng, Xiaopeng Wu, Xubin Li, Tiezheng Ge, Bo Zheng, and Yong Liu. 2025a. Do not abstain! identify and solve the uncertainty. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17177–17197. find
  44. Runze Liu, Junqi Gao, Jian Zhao, Kaiyan Zhang, Xiu Li, Biqing Qi, Wanli Ouyang, and Bowen Zhou. 2025b. Can 1b llm surpass 405b llm? rethinking compute-optimal test-time scaling. arXiv preprint arXiv:2502.06703.
  45. Victor Quach, Adam Fisch, Tal Schuster, Adam Yala, Jae Ho Sohn, Tommi S Jaakkola, and Regina Barzilay. 2023. Conformal language modeling. In The Twelfth International Conference on Learning Representations. find
  46. Xiaoou Liu, Tiejin Chen, Longchao Da, Chacha Chen, Zhen Lin, and Hua Wei. 2025c. Uncertainty quantification and confidence calibration in large language models: A survey. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pages 6107–6117.
  47. Ali Razghandi, Seyed Mohammad Hadi Hosseini, and Mahdieh Soleymani Baghshah. 2025. Cer: Confidence enhanced reasoning in llms. arXiv preprint arXiv:2502.14634.
  48. Yuliang Liu, Junjie Lu, Zhaoling Chen, Chaofeng Qu, Jason Klein Liu, Chonghan Liu, Zefan Cai, Yunhui Xia, Li Zhao, Jiang Bian, and 1 others. 2025d. Adaptivestep: Automatically dividing reasoning step through model confidence. arXiv preprint arXiv:2502.13943. — [arXiv:2502.13943](https://arxiv.org/abs/2502.13943) find
  49. Xingzhou Lou, Dong Yan, Wei Shen, Yuzi Yan, Jian Xie, and Junge Zhang. 2024. Uncertainty-aware reward model: Teaching reward models to know what is unknown. arXiv preprint arXiv:2410.00847. — [arXiv:2410.00847](https://arxiv.org/abs/2410.00847) find
  50. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori B Hashimoto. 2025. s1: Simple test-time scaling. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages…
  51. Jianfeng Pan, Senyou Deng, and Shaomang Huang. 2025. Coat: Chain-of-associated-thoughts framework for enhancing large language models reasoning. arXiv preprint arXiv:2502.02390. find
  52. Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, and Deepak Pathak. 2025. Maximizing confidence alone improves reasoning. arXiv preprint arXiv:2505.22660. — [arXiv:2505.22660](https://arxiv.org/abs/2505.22660) find
  53. Xiao Pu, Michael Saxon, Wenyue Hua, and William Yang Wang. 2025. Thoughtterminator: Benchmarking, calibrating, and mitigating overthinking in reasoning models. arXiv preprint arXiv:2504.13367. — [arXiv:2504.13367](https://arxiv.org/abs/2504.13367) find
  54. Chen Qian, Dongrui Liu, Haochen Wen, Zhen Bai, Yong Liu, and Jing Shao. 2025a. Demystifying reasoning dynamics with mutual information: Thinking tokens are information peaks in llm reasoning. arXiv preprint arXiv:2506.02867. — [arXiv:2506.02867](https://arxiv.org/abs/2506.02867) find
  55. Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tur, Gokhan Tur, and Heng Ji. 2025b. Smart: Self-aware agent for tool overuse mitigation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4604– 4621. find
  56. Linlu Qiu, Fei Sha, Kelsey Allen, Yoon Kim, Tal Linzen, and Sjoerd van Steenkiste. 2025. Bayesian teaching enables probabilistic reasoning in large language models. arXiv preprint arXiv:2503.17523. — [arXiv:2503.17523](https://arxiv.org/abs/2503.17523) find
  57. Brendan Leigh Ross, NoÃG , l Vouitsis, Atiyeh Ashari Ghomi, Rasa Hosseinzadeh, Ji Xin, Zhaoyan Liu, Yi Sui, Shiyi Hou, Kin Kwan Leung, Gabriel Loaiza-Ganem, and 1 others. 2025. Textual bayes: Quantifying uncertainty in llm-based systems. arXiv preprint arXiv:2506.10060. — [arXiv:2506.10060](https://arxiv.org/abs/2506.10060) find
  58. John Schulman and Thinking Machines Lab. 2025. Lora without regret. Thinking Machines Lab: Connectionism. Https://thinkingmachines.ai/blog/lora/. find
  59. David Antony Selby, Kai Spriestersbach, Yuichiro Iwashita, Dennis Bappert, Archana Warrier, Sumantrak Mukherjee, Muhammad Nabeel Asim, Koichi Kise, and Sebastian Josef Vollmer. 2024. Had enough of experts? elicitation and evaluation of bayesian priors from large language models. In NeurIPS 2024 Work… find
  60. Ola Shorinwa, Zhiting Mei, Justin Lidard, Allen Z Ren, and Anirudha Majumdar. 2025. A survey on uncertainty quantification of large language models: Taxonomy, open research challenges, and future directions. ACM Computing Surveys. find
  61. Ryan Smith, Jason A Fries, Braden Hancock, and Stephen H Bach. 2024. Language models in the loop: Incorporating prompting into weak supervision. ACM/JMS Journal of Data Science, 1(2):1–30. find
  62. Josefa Lia Stoisser, Marc Boubnovski Martell, Lawrence Phillips, Gianluca Mazzoni, Lea Mørch Harder, Philip Torr, Jesper Ferkinghoff-Borg, Kaspar Martens, and Julien Fauqueur. 2025. Towards agents that know when they don’t know: Uncertainty as a control signal for structured reasoning. arXiv preprin… — [arXiv:2509.02401](https://arxiv.org/abs/2509.02401) find
  63. Jiayuan Su, Jing Luo, Hongwei Wang, and Lu Cheng. 2024. Api is enough: Conformal prediction for large language models without logit-access. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 979–995. find
  64. Zhiqing Sun, Longhui Yu, Yikang Shen, Weiyang Liu, Yiming Yang, Sean Welleck, and Chuang Gan. 2024. Easy-to-hard generalization: Scalable alignment beyond human supervision. Advances in Neural Information Processing Systems, 37:51118–51168. find
  65. Amir Taubenfeld, Tom Sheffer, Eran Ofek, Amir Feder, Ariel Goldstein, Zorik Gekhman, and Gal Yona. 2025. Confidence improves self-consistency in llms. arXiv preprint arXiv:2502.06233. find
  66. Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, and Christopher D Manning. 2023. Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. In Proceedings of the 2023 Confer… find
  67. Carel van Niekerk, Renato Vukovic, Benjamin Matthias Ruppik, Hsien-chin Lin, and Milica Gašić. 2025. Post-training large language models via reinforcement learning from self-feedback. arXiv preprint arXiv:2507.21931. — [arXiv:2507.21931](https://arxiv.org/abs/2507.21931) find
  68. Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev, Lyudmila Rvanova, Daniil Vasilev, Akim Tsvigun, Sergey Petrakov, Rui Xing, Abdelrahman Sadallah, Kirill Grishchenkov, and 1 others. 2025. Benchmarking uncertainty quantification methods for large language models with lm-polygraph. Transactions of…
  69. Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, and Ke Wang. 2025a. Harnessing uncertainty: Entropy-modulated policy gradients for long-horizon llm agents. arXiv preprint arXiv:2509.09265. — [arXiv:2509.09265](https://arxiv.org/abs/2509.09265) find
  70. Jingyao Wang, Wenwen Qiang, Zeen Song, Changwen Zheng, and Hui Xiong. 2025b. Learning to think: Information-theoretic reinforcement fine-tuning for llms. arXiv preprint arXiv:2505.10425. — [arXiv:2505.10425](https://arxiv.org/abs/2505.10425) find
  71. Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xionghui Chen, Jianxin Yang, Zhenru Zhang, and 1 others. 2025c. Beyond the 80/20 rule: High-entropy minority tokens drive effective reinforcement learning for llm reasoning. arXiv preprint arXiv:2506.01939.
  72. Tao Wang, Daniel Lizotte, Michael Bowling, and Dale Schuurmans. 2005. Bayesian sparse sampling for on-line reward optimization. In Proceedings of the 22nd international conference on Machine learning, pages 956–963. find
  73. Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, and Mengting Hu. 2025d. Ubench: Benchmarking uncertainty in large language models with multiple choice questions. In Findings of the Association for Computational Linguistics: ACL 2025, pag… find
  74. Zhihai Wang, Jie Wang, Jilai Pan, Xilin Xia, Huiling Zhen, Mingxuan Yuan, Jianye Hao, and Feng Wu. 2025e. Accelerating large language model reasoning via speculative search. arXiv preprint arXiv:2505.02865. — [arXiv:2505.02865](https://arxiv.org/abs/2505.02865) find
  75. Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, and Xiaofeng Zhu. 2024. Conu: Conformal uncertainty in large language models with correctness coverage guarantees. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 688… find
  76. Lilian Weng. 2024. Reward hacking in reinforcement learning. lilianweng.github.io. find
  77. Piotr Wilczyński, Wiktoria Mieleszczenko-Kowszewicz, and Przemysław Biecek. 2024. Resistance against manipulative ai: key factors and possible actions. In ECAI 2024, pages 802–809. IOS Press. find
  78. Heming Xia, Chak Tou Leong, Wenjie Wang, Yongqi Li, and Wenjie Li. 2025a. Tokenskip: Controllable chain-of-thought compression in llms. arXiv preprint arXiv:2502.12067.
  79. Zhiqiu Xia, Jinxuan Xu, Yuqian Zhang, and Hang Liu. 2025b. A survey of uncertainty estimation methods on large language models. arXiv preprint arXiv:2503.00172. find
  80. Miao Xiong, Zhiyuan Hu, Xinyang Lu, YIFEI LI, Jie Fu, Junxian He, and Bryan Hooi. 2024. Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms. In The Twelfth International Conference on Learning Representations. find
  81. Boyang Xue, Fei Mi, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Erxin Yu, Xuming Hu, and Kam-Fai Wong. 2025. Ualign: Leveraging uncertainty estimations for factuality alignment on large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume… find
  82. Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Luu Anh Tuan, Haiteng Zhao, Qika Lin, and 1 others. 2025a. Mur: Momentum uncertainty guided reasoning for large language models. arXiv preprint arXiv:2507.14958.
  83. Hanqi Yan, Linhai Zhang, Jiazheng Li, Zhenyi Shen, and Yulan He. 2025b. Position: Llms need a bayesian meta-reasoning framework for more robust and generalizable reasoning. In 2025 International Conference on Machine Learning: ICML25. find
  84. Adam X Yang, Maxime Robeyns, Thomas Coste, Zhengyan Shi, Jun Wang, Haitham Bou-Ammar, and Laurence Aitchison. 2024. Bayesian reward models for llm alignment. arXiv preprint arXiv:2402.13210. — [arXiv:2402.13210](https://arxiv.org/abs/2402.13210) find
  85. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.
  86. Fanghua Ye, Mingming Yang, Jianhui Pang, Longyue Wang, Derek Wong, Emine Yilmaz, Shuming Shi, and Zhaopeng Tu. 2024. Benchmarking llms via uncertainty quantification. Advances in Neural Information Processing Systems, 37:15356–15385. find
  87. Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Xuan-Jing Huang. 2023. Do large language models know what they don’t know? In Findings of the Association for Computational Linguistics: ACL 2023, pages 8653–8665. find
  88. Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Junqi Dai, Qinyuan Cheng, Xuan-Jing Huang, and Xipeng Qiu. 2024. Reasoning in flux: Enhancing large language models reasoning through uncertainty-aware adaptive guidance. In Proceedings of the 62nd Annual Meeting of the Association for… find
  89. Han Zhong, Yutong Yin, Shenao Zhang, Xiaojun Xu, Yuanxin Liu, Yifei Zuo, Zhihan Liu, Boyi Liu, Sirui Zheng, Hongyi Guo, and 1 others. 2025. Brite: Bootstrapping reinforced thinking process to enhance language model reasoning. arXiv preprint arXiv:2501.18858. — [arXiv:2501.18858](https://arxiv.org/abs/2501.18858) find
  90. Jiaxin Zhang. 2021. Modern monte carlo methods for efficient uncertainty quantification and propagation: A survey. Wiley Interdisciplinary Reviews: Computational Statistics, 13(5):e1539. find
  91. Jiaxin Zhang. 2025. Confidence-aware reasoning: Optimizing self-guided thinking trajectories in large reasoning models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2081–2095. find
  92. Jiaxin Zhang, Prafulla Kumar Choubey, Kung-Hsiang Huang, Caiming Xiong, and Chien-Sheng Wu. 2026a. Agentic uncertainty quantification. arXiv preprint arXiv:2601.15703. — [arXiv:2601.15703](https://arxiv.org/abs/2601.15703) find
  93. Jiaxin Zhang, Zhuohang Li, Kamalika Das, Bradley Malin, and Sricharan Kumar. 2023. Sac3: reliable hallucination detection in black-box language models via semantic-aware cross-check consistency. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15445–15458.
  94. Jiaxin Zhang, Caiming Xiong, and Chien-Sheng Wu. 2026b. Agentic confidence calibration. arXiv preprint arXiv:2601.15778. — [arXiv:2601.15778](https://arxiv.org/abs/2601.15778) find
  95. Jiaxin Zhang, Caiming Xiong, and Jason Wu. 2025a. Agentic confidence calibration. preprint. find
  96. Qingyang Zhang, Haitao Wu, Changqing Zhang, Peilin Zhao, and Yatao Bian. 2025b. Right question is already half the answer: Fully unsupervised llm reasoning incentivization. arXiv preprint arXiv:2504.05812. find
  97. Qiwei Zhao, Xujiang Zhao, Yanchi Liu, Wei Cheng, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Huaxiu Yao, and Haifeng Chen. 2024. Saup: Situation awareness uncertainty propagation on llm agent. arXiv preprint arXiv:2412.01033. find
  98. Xuandong Zhao, Zhewei Kang, Aosong Feng, Sergey Levine, and Dawn Song. 2025a. Learning to reason without external rewards. arXiv preprint arXiv:2505.19590. find
  99. Xutong Zhao, Tengyu Xu, Xuewei Wang, Zhengxing Chen, Di Jin, Liang Tan, Zishun Yu, Zhuokai Zhao, Yun He, Sinong Wang, and 1 others. 2025b. Boosting llm reasoning via spontaneous self-correction. arXiv preprint arXiv:2506.06923. — [arXiv:2506.06923](https://arxiv.org/abs/2506.06923) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-passive-metric-active-signal-evolving/