diff --git a/README.md b/README.md index db66bde..d272477 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,7 @@ ## ๐Ÿ“ฐ News +- **2026-07-08** ๐Ÿงต **Per-case agent trajectories released** โ€” browse the best hybrid GUI+CLI rollout for every one of the 114 tasks (thinking ยท actions ยท screenshots ยท deliverables ยท judge scores), bilingual viewer. [Trajectory gallery](https://weavebench.github.io/trajectories/) - **2026-06-30** ๐Ÿš€ **OSWorld-V2 hybrid GUI+CLI harness** โ€” GPT-5.5 gains **+5.5 pt** Binary (13.0โ†’18.5%) at ~2ร— tool-call efficiency. [`experiments/osworld_v2_hybrid/`](./experiments/osworld_v2_hybrid) - **2026-06-12** ๐ŸŽ‰ Ranked **#4 on [HF Daily Papers](https://huggingface.co/papers/2606.09426)** with **104 upvotes**. - **2026-06-08** Initial preprint + [project website](https://weavebench.github.io) live.