NEWS · RESEARCH · #148
AutoTailor: Automatic, user-aligned capability selection and adaptation for web agents
AutoTailor is a meta-agentic framework that converts web interaction trajectories into parameterized browser-automation APIs, applies offline Quality and Usage Likelihood filters to remove redundant or low-value APIs, and uses online Dynamic Reselection to add missing capabilities and prune persistently unused ones. Evaluated on 106 WebArena Postmill tasks, offline filtering reduced 1,283 initial APIs to 87 and Dynamic Reselection yielded a 33-API set; with a ReAct fallback this set achieved 90.6% correctness (vs. 87.5% for ReAct alone) while cutting request-token cost by 57.8% and latency by 29.4%, and without ReAct it reached 60.1% correctness while reducing request-token usage by 94.9%.
KEY POINTS
- AutoTailor is a meta-agentic framework that converts web interaction trajectories into parameterized browser-automation APIs, applies offline Quality and Usage Likelihood filters to remove redundant or low-value APIs, and uses online Dynamic Reselection to add missing capabilities and prune persistently unused ones.
- Evaluated on 106 WebArena Postmill tasks, offline filtering reduced 1,283 initial APIs to 87 and Dynamic Reselection yielded a 33-API set; with a ReAct fallback this set achieved 90.6% correctness (vs.
- 87.5% for ReAct alone) while cutting request-token cost by 57.8% and latency by 29.4%, and without ReAct it reached 60.1% correctness while reducing request-token usage by 94.9%.
WHY IT MATTERS
This work demonstrates that combined static filtering and dynamic, usage-driven adaptation can produce compact, user-aligned capability sets that improve web-agent accuracy and substantially reduce token cost and latency.