WebAnything rebuilds real websites into reusable agent environments
Fine-tuning Qwen3.5-9B on 5,856 trajectories lifts WebArena-Verified overall success by 13.33 points.
2 stories, newest first · one card per story
Fine-tuning Qwen3.5-9B on 5,856 trajectories lifts WebArena-Verified overall success by 13.33 points.
Skill2Env synthesizes executable agent environments from skills; fine-tuning on 1,500 trajectories improves benchmarks.
Today 2K readers · 8.9K views · 7K reads · all time 155K views