English

Towards Uncertainty-Aware Language Agent

Computation and Language 2024-05-31 v3

Abstract

While Language Agents have achieved promising success by placing Large Language Models at the core of a more versatile design that dynamically interacts with the external world, the existing approaches neglect the notion of uncertainty during these interactions. We present the Uncertainty-Aware Language Agent (UALA), a framework that orchestrates the interaction between the agent and the external world using uncertainty quantification. Compared with other well-known counterparts like ReAct, our extensive experiments across 3 representative tasks (HotpotQA, StrategyQA, MMLU) and various LLM sizes demonstrate that UALA brings a significant improvement of performance, while having a substantially lower reliance on the external world (i.e., reduced number of tool calls and tokens). Our analyses provide various insights including the great potential of UALA compared with agent fine-tuning, and underscore the unreliability of verbalised confidence of LLMs as a proxy for uncertainty.

Keywords

Cite

@article{arxiv.2401.14016,
  title  = {Towards Uncertainty-Aware Language Agent},
  author = {Jiuzhou Han and Wray Buntine and Ehsan Shareghi},
  journal= {arXiv preprint arXiv:2401.14016},
  year   = {2024}
}

Comments

Our code and data are at https://uala-agent.github.io. (accepted to ACL 2024 Findings). arXiv admin note: text overlap with arXiv:2310.05915

R2 v1 2026-06-28T14:26:47.553Z