# Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents

arXiv: https://arxiv.org/abs/2608.11552 · HTML: https://mlsanity.com/paper/2608.11552/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 17 of 17)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making](https://mlsanity.com/paper/2506.17419/) (2025)
- [Structured Uncertainty guided Clarification for LLM Agents](https://mlsanity.com/paper/2511.08798/) (2025)
- [Atomic Calibration of LLMs in Long-Form Generations](https://mlsanity.com/paper/2410.13246/) (2024)
- [Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities](https://mlsanity.com/paper/2602.05073/) (2026)
- [Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers](https://mlsanity.com/paper/2504.19254/) (2025)
- [The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents](https://mlsanity.com/paper/2601.07264/) (2026)
- [Confidence Estimation for LLMs in Multi-turn Interactions](https://mlsanity.com/paper/2601.02179/) (2026)
- [Graph-based Uncertainty Metrics for Long-form Language Model Outputs](https://mlsanity.com/paper/2410.20783/) (2024)
- [EAGer: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling](https://mlsanity.com/paper/2510.11170/) (2025)
- [Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study](https://mlsanity.com/paper/2602.17431/) (2026)

## Built on by (most cited first, 1 of 1)

- [Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents](https://mlsanity.com/paper/2610.07948/) (2026)

## Abstract (arXiv)

Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one generated answer. For LLM agents, however, the unit of observation is an interactive trajectory, where the model can ask clarifying questions, call tools, update state, and make intermediate decisions whose errors propagate to the final outcome. We study whether three common families of single-turn UQ methods transfer to this setting. Across five LLMs and four multi-turn tool-use datasets from BFCL-v4 and τ2-bench, we evaluate white-box scorers based on action-token probabilities, black-box consistency scorers based on resampled trajectories, and reflexive scorers based on model self-assessment of the trajectory. We find that transfer is often useful but uneven. Token-probability scores are highly sensitive to the choice of aggregator used across turns, reflexive scores provide the strongest low-cost baseline in most evaluated settings, and black-box self-consistency is often the strongest UQ family, with trajectory-equivalence and action-set consistency typically ranking highest among its variants. These results suggest that UQ methods developed for single generations should be revalidated at the trajectory level, with careful attention to the consistency measurement, aggregator choice, and computational budget.