mlsanityData to 7 Oct 2026

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

arXiv 2510.11221 ↗First posted 13 Oct 2025cs.CLcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

23 of 27 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Magentic-UI: Towards Human-in-the-loop Agentic Systems30 Jul
  2. 2024A Unified Approach to Routing and Cascading for LLMs14 Oct

Other references · 21

  1. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  2. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  3. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  4. 2016Deep Variational Information Bottleneckcited by 915
  5. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Modelscited by 424
  6. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 180
  7. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  8. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  9. 2024OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesiscited by 155
  10. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 141
  11. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 140
  12. 2025Harnessing Multiple Large Language Models: A Survey on LLM Ensemblecited by 86
9 more
  1. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 84
  2. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  3. 2024Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaborationcited by 66
  4. 2024Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoningcited by 38
  5. 2024AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistantcited by 27
  6. 2025Visual Test-time Scaling for GUI Agent Groundingcited by 27
  7. 2025Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selectioncited by 23
  8. 2025Build the web for agents, not agents for the webcited by 17
  9. 2025RLAE: Reinforcement Learning-Assisted Ensemble for LLMscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agentscited by 1
  2. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning Agent Routing From Early Experience
  2. 2026Agent-as-a-Router: Agentic Model Routing for Coding Tasks
  3. 2026AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows
  4. 2026TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
  5. 2026ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
  6. 2026WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
  7. 2026Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
  8. 2025Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference