developer tools
The Web Agent Learned the Application Before Spending Tokens
On 45 Canvas tasks, OdoBot used 44% and 80% fewer tokens than two agent baselines while beating one on task success.
Summary
On 45 Canvas tasks, OdoBot used 44% and 80% fewer tokens than two agent baselines while beating one on task success.
Conventional web agents repeatedly inspect an interface and reason about low-level interactions. OdoBot instead builds an application behavior model from successful demonstrations, then uses that reusable structure to execute natural-language tasks. On 45 tasks in the Canvas learning-management system, the authors report 44% fewer tokens than Agent-E and 80% fewer than WebVoyager, while also surpassing WebVoyager’s task-success rate. The evaluation is limited to one application and task set, but it suggests that explicit behavior models can replace a costly share of repeated visual reasoning.
Why it matters
On 45 Canvas tasks, OdoBot used 44% and 80% fewer tokens than two agent baselines while beating one on task success.
Limits and context
No additional limitation was separately recorded.
Key claims
On 45 Canvas tasks, OdoBot used 44% and 80% fewer tokens than two agent baselines while beating one on task success.
Evidence: source-2026-09-15-009
Sources
- arXiv preprint 2609.13491arXiv · primary research
Corrections
No corrections have been recorded for this story.