Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.05073 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911605298561024 |
|---|---|
| author | Oh, Changdae Park, Seongheon Kim, To Eun Li, Jiatong Li, Wendi Yeh, Samuel Du, Xuefeng Hassani, Hamed Bogdan, Paul Song, Dawn Li, Sharon |
| author_facet | Oh, Changdae Park, Seongheon Kim, To Eun Li, Jiatong Li, Wendi Yeh, Samuel Du, Xuefeng Hassani, Hamed Bogdan, Paul Song, Dawn Li, Sharon |
| contents | Uncertainty quantification (UQ) for large language models (LLMs) is a key building block for safety guardrails of daily LLM applications. Yet, even as LLM agents are increasingly deployed in highly complex tasks, most UQ research still centers on single-turn question-answering. We argue that UQ research must shift to realistic settings with interactive agents, and that a new principled framework for agent UQ is needed. This paper presents three pillars to build a solid ground for future agent UQ research: (1. Foundations) We present the first general formulation of agent UQ that subsumes broad classes of existing UQ setups; (2. Challenges) We identify four technical challenges specifically tied to agentic setups -- selection of uncertainty estimator, uncertainty of heterogeneous entities, modeling uncertainty dynamics in interactive systems, and lack of fine-grained benchmarks -- with numerical analysis on a real-world agent benchmark, $τ^2$-bench; (3. Future Directions) We conclude with noting on the practical implications of agent UQ and remaining open problems as forward-looking discussion for future explorations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05073 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities Oh, Changdae Park, Seongheon Kim, To Eun Li, Jiatong Li, Wendi Yeh, Samuel Du, Xuefeng Hassani, Hamed Bogdan, Paul Song, Dawn Li, Sharon Artificial Intelligence Uncertainty quantification (UQ) for large language models (LLMs) is a key building block for safety guardrails of daily LLM applications. Yet, even as LLM agents are increasingly deployed in highly complex tasks, most UQ research still centers on single-turn question-answering. We argue that UQ research must shift to realistic settings with interactive agents, and that a new principled framework for agent UQ is needed. This paper presents three pillars to build a solid ground for future agent UQ research: (1. Foundations) We present the first general formulation of agent UQ that subsumes broad classes of existing UQ setups; (2. Challenges) We identify four technical challenges specifically tied to agentic setups -- selection of uncertainty estimator, uncertainty of heterogeneous entities, modeling uncertainty dynamics in interactive systems, and lack of fine-grained benchmarks -- with numerical analysis on a real-world agent benchmark, $τ^2$-bench; (3. Future Directions) We conclude with noting on the practical implications of agent UQ and remaining open problems as forward-looking discussion for future explorations. |
| title | Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.05073 |