# WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent

arXiv: https://arxiv.org/abs/2510.11221 · HTML: https://mlsanity.com/paper/2510.11221/

## Key facts

- Cited by 2 papers in the map (data through 13 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 23 of 23)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)
- [Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models](https://mlsanity.com/paper/2311.08692/) (2023)
- [Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning](https://mlsanity.com/paper/2310.03094/) (2023)
- [Harnessing Multiple Large Language Models: A Survey on LLM Ensemble](https://mlsanity.com/paper/2502.18036/) (2025)
- [RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models](https://mlsanity.com/paper/2409.19886/) (2024)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration](https://mlsanity.com/paper/2404.12715/) (2024)
- [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://mlsanity.com/paper/2507.22358/) (2025)
- [Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning](https://mlsanity.com/paper/2412.15797/) (2024)
- [Visual Test-time Scaling for GUI Agent Grounding](https://mlsanity.com/paper/2505.00684/) (2025)
- [AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant](https://mlsanity.com/paper/2410.18603/) (2024)
- [Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection](https://mlsanity.com/paper/2505.19435/) (2025)
- [Build the web for agents, not agents for the web](https://mlsanity.com/paper/2506.10953/) (2025)
- [RLAE: Reinforcement Learning-Assisted Ensemble for LLMs](https://mlsanity.com/paper/2506.00439/) (2025)

## Built on by (most cited first, 2 of 2)

- [Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents](https://mlsanity.com/paper/2608.06171/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

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.