Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.17821 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908982231171072 |
|---|---|
| author | Zhang, Lingfeng Sun, Yongan Hu, Jinpeng Ma, Hui Ying, Yang Liu, Kuien Shi, Zenglin Wang, Meng |
| author_facet | Zhang, Lingfeng Sun, Yongan Hu, Jinpeng Ma, Hui Ying, Yang Liu, Kuien Shi, Zenglin Wang, Meng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17821 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent Zhang, Lingfeng Sun, Yongan Hu, Jinpeng Ma, Hui Ying, Yang Liu, Kuien Shi, Zenglin Wang, Meng Artificial Intelligence 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. |
| title | WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17821 |