Practical AI/Brief

New Web Agent Uses Up to 80% Fewer Tokens Than Competitors

A new research paper introduces OdoBot, a web-agent architecture that completes tasks with fewer tokens by modeling application behavior from demonstrations.

BriefPublished 15 September 20261 min read1 linked source · 4 checked facts

Token use reduction: 44% and 80% % — Original graphic: drawn from the figures in this story, not a stock image.

The paper describes OdoBot as a web agent that automates tasks described in natural language by analyzing a web application's user interface. Unlike conventional agents, it builds a behavioral model of the application from successful task-execution demonstrations.

In experiments on 45 tasks using the Canvas Learning Management System, OdoBot used 44% and 80% fewer tokens than Agent-E and WebVoyager, respectively, and also surpassed WebVoyager in task success rate. The practical detail: lower token use means lower cost for running web agents.

What the reporting says

Each line below is stated by the page named above it, and only by that page.

Stated by arXiv

OdoBot is a web-agent architecture that completes tasks at a fraction of the cost when compared to conventional web agents.
It leverages a behavioral model of the underlying application constructed by analyzing successful task-execution demonstrations.
Experiments with 45 tasks on the Canvas Learning Management System (LMS) demonstrate that OdoBot uses 44% and 80% fewer tokens than Agent-E and WebVoyager.
OdoBot surpasses WebVoyager in terms of task success rate.

Our view

If the token savings generalize beyond the Canvas LMS, this could make web automation more affordable for everyday use.

What the reporting says: OdoBot uses 44% and 80% fewer tokens than Agent-E and WebVoyager, while also surpassing WebVoyager in terms of task success rate.

Sources

arXivText stored 15 September 2026 · checked 15 September 2026

Found through monitored feeds: arXiv. A feed address is how the desk finds a story, not the evidence for it — the sources listed above are the pages the facts were taken from.

How this story was checked. Written from the 1 page listed above, stored 15 September 2026; claims checked against that stored text on 15 September 2026.

What that means

4 of 4 reported statements were confirmed against the page that carries them; the rest were removed rather than published.
Figures in the text were required to appear in the stored source text: yes. Identifiers: yes.
The check reads stored text only: no claim rests on a fresh look that did not happen.
Where the reporting was silent, the text says so instead of filling the gap.

New Web Agent Uses Up to 80% Fewer Tokens Than Competitors

What the reporting says

Our view

Sources

More from Practical AI

New method explains self-driving car AI decisions in real time

Autonomous AI Agents: What They Can Do and How to Manage the Risks

ChatGPT ads now open a conversation instead of a website

What the reporting says

Our view

Sources

Related reading

Web agent OdoBot cuts token use in Canvas LMS tests, preprint reports

More from Practical AI

New method explains self-driving car AI decisions in real time

Autonomous AI Agents: What They Can Do and How to Manage the Risks

ChatGPT ads now open a conversation instead of a website