Token Efficient Task Execution via Application Behavior Modeling for Web Agents

A new web-agent architecture called OdoBot completes web-application tasks using 44% and 80% fewer tokens than the state-of-the-art agents Agent-E and WebVoyager, respectively, according to an arXiv paper (arXiv:2609.13491v1). OdoBot builds a behavioral model of the underlying application from successful task-execution demonstrations, and in experiments across 45 tasks on the Canvas Learning Management System it also surpassed WebVoyager on task success rate. The work targets the rising token-processing costs of agentic infrastructure.

arXiv:2609.13491v1 Announce Type: new Abstract: 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.