mlsanityData to 7 Oct 2026

Token Efficient Task Execution via Application Behavior Modeling for Web Agents

arXiv 2609.13491 ↗First posted 11 Sep 2026cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

The strong performance of AI Agents across an impressive variety of tasks is driving an unprecedented investment in agentic infrastructures, however the cost of processing tokens is fast increasing. Web agents automate the execution of web-application tasks described in natural language, by analyzing the web-application's user interface (UI) and interacting with it. This work introduces OdoBot, a novel web-agent architecture that completes tasks at a fraction of the cost when compared to conventional web agents. This is achieved by leveraging a behavioral model of the underlying application constructed by analyzing successful task-execution demonstrations. Our experiments with 45 tasks on the Canvas Learning Management System (LMS) demonstrate that OdoBot uses 44% and 80% fewer tokens than two state-of-the-art competitor agents (Agent-E and WebVoyager), while also surpassing WebVoyager in terms of task success rate.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 15 of its 23 references that are in the map. First posted on arXiv 11 Sep 2026.

Builds on

15 of 23 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models30 Mar
  2. 2024NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild3 Oct
  3. 2024Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems17 Jul
  4. 2024WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents8 Apr
  5. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?12 Mar
  6. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models25 Jan
  7. 2024GPT-4V(ision) is a Generalist Web Agent, if Grounded3 Jan
  8. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul
  9. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun

Other references · 6

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 180
  4. 2024The rising costs of training frontier AI modelscited by 91
  5. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  6. 2024A Systematic Review of Generative AI for Teaching and Learning Practicecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Beyond Browsing: API-Based Web Agents
  2. 2026Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild
  3. 2025REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites
  4. 2025Agentic Web: Weaving the Next Web with AI Agents
  5. 2026The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge
  6. 2026WebChallenger: A Reliable and Efficient Generalist Web Agent
  7. 2025Build the web for agents, not agents for the web
  8. 2026AI Planning Framework for LLM-Based Web Agents