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

TL;DR

WebUncertainty introduces a dual-level uncertainty framework for autonomous web agents, enhancing planning and reasoning to better handle complex, dynamic web tasks with improved decision-making.

Contribution

It presents a novel dual-level uncertainty approach with adaptive planning and Monte Carlo tree search, addressing limitations of existing web agents in complex environments.

Findings

Outperforms state-of-the-art baselines on WebArena and WebVoyager benchmarks.

Effectively quantifies both aleatoric and epistemic uncertainties to guide decision-making.

Demonstrates robustness in dynamic, long-horizon web tasks.

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 long-horizon 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 WebVoyager benchmarks demonstrate that WebUncertainty achieves superior performance compared to state-of-the-art baselines.