Research area: Computer Vision Authors: Minh Pham-Dinh, Md Farhan Ishmam, Hernan Yupanqui, Reaz Hassan Joarder, Kenneth Marino Published: 2026-10-26 arXiv: 2610.35823
Abstract
Browser agents do not just need more practice. They need to practice the right things. The authors introduce MiniWeb, a realistic miniature of the web comprising 65 interconnected websites across 15 domains, where agents navigate, search, and transact as people do. Its 369 human-annotated tasks cover everyday workflows and label 37 reusable interaction primitives grouped into 7 skill families, allowing diagnosis of which skills fail rather than only whether a task succeeds.
Benchmarking ten open-weight agents, they find that drag & gesture is consistently the weakest family, with no agent solving more than 24% of its instances.
To address this gap, they introduce MiniWebGen, a framework that autonomously generates verified, skill-centric training data from MiniWeb. Fine-tuning Qwen3.5-4B on just 3.1K verified trajectories improves single-primitive success by 24.9pp across 13 unseen websites, with gains across every skill family. However, these trajectories teach short-horizon interactions, which do not directly translate to full-task success.
Building on this result, they construct MiniWebAgent, which pairs the trained executor with a planner that decomposes full tasks into the skill-level steps it learned to perform. This approach improves task success by 19.4pp on unseen MiniWeb sites and transfers to external benchmarks, with gains of 9.3pp on WebArena-Lite, 16.1pp on Online-Mind2Web, and 20.0pp on WebVoyager, without training on their trajectories.
The recipe is simple: practice reusable skills directly, then compose them to solve unfamiliar tasks.
---
*Auto-collected on 2026-10-28.*