Work

WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent

Year: 2026

Type: conference-paper

Abstract: Recent advancements in large language models (LLMs) have empowered autonomous web agents to execute natural language instructions directly on real-world webpages.However, existing agents often struggle with complex tasks involving dynamic interactions and longhorizon execution due to rigid planning strategies and hallucination-prone reasoning.To address these limitations, we propose WebUncertainty, a novel autonomous agent framework designed to tackle dual-level uncertainty in planning and reasoning.Specifically, we design a Task Uncertainty-Driven Adaptive Planning Mechanism that adaptively selects planning modes to navigate unknown environments.Furthermore, we introduce an Action Uncertainty-Driven Monte Carlo tree search (MCTS) Reasoning Mechanism.This mechanism incorporates the Confidence-induced Action Uncertainty (ConActU) strategy to quantify both aleatoric uncertainty (AU) and epistemic uncertainty (EU), thereby optimizing the search process and guiding robust decision-making.Experimental results on the WebArena and We-bVoyager benchmarks demonstrate that We-bUncertainty achieves superior performance compared to state-of-the-art baselines.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.637