WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent
Year: 2025
Type: preprint
Abstract: LLM-brained web agents offer powerful capabilities for web automation but face a critical cost-performance trade-off. The challenge is amplified by web agents' inherently complex prompts that include goals, action histories, and environmental states, leading to degraded LLM ensemble performance. To address this, we introduce WebRouter, a novel query-specific router trained from an information-theoretic perspective. Our core contribution is a cost-aware Variational Information Bottleneck (ca-VIB) objective, which learns a compressed representation of the input prompt while explicitly penalizing the expected operational cost. Experiments on five real-world websites from the WebVoyager benchmark show that WebRouter reduces operational costs by a striking 87.8\% compared to a GPT-4o baseline, while incurring only a 3.8\% accuracy drop.
Source: arXiv (Cornell University)
Authors: Li, Tao, Hu, Jinlong, Wang, Yang, Liu, Junfeng, Liu, Xuejun
Language: English
Topic: Web Data Mining and Analysis
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7091187670
Cites:
Cited by:
Related to: