WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent
It addresses the problem of rigid planning and hallucination-prone reasoning in LLM-based web agents, improving their ability to handle complex, dynamic web tasks.
WebUncertainty introduces a dual-level uncertainty-driven framework for autonomous web agents, achieving superior performance on WebArena and WebVoyager benchmarks compared to state-of-the-art baselines.
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.