diff --git a/.gitmodules b/.gitmodules
deleted file mode 100644
index b0f5705..0000000
--- a/.gitmodules
+++ /dev/null
@@ -1,3 +0,0 @@
-[submodule "autogen"]
- path = autogen
- url = https://github.com/microsoft/autogen.git
diff --git a/README.md b/README.md
index ce5122f..9963b75 100644
--- a/README.md
+++ b/README.md
@@ -1,17 +1,17 @@
-# Fara-7B: An Efficient Agentic Model for Computer Use
+# Fara1.5 – A family of frontier computer use agent models
-

+

-[](https://aka.ms/msaif/fara)
-[](https://huggingface.co/microsoft/Fara-7b)
-[](https://aka.ms/foundry-fara-7b)
+[](https://aka.ms/fara1.5)
+[](https://arxiv.org/abs/2606.20785)
+[](https://www.microsoft.com/en-us/research/articles/fara1-5-computer-use-agent/)
+[](https://ai.azure.com/catalog/models/Fara1.5-9B)
[](https://huggingface.co/datasets/microsoft/WebTailBench)
[](https://huggingface.co/datasets/microsoft/CUAVerifierBench)
-[](https://arxiv.org/abs/2511.19663)
@@ -19,14 +19,22 @@
## Updates
-* **2026-05-21** - Fara1.5 agent harness coming soon!
-* **2026-05-12** — Refreshed **WebTailBench (V2)** tasks and rubrics.
- Many V1 tasks had calendar-bound dates that expired (Nov 2025); V2
- rolls those forward and revises the precomputed rubrics for the
- full 609-task suite. Available now as the `test_v2` split on
- [`microsoft/WebTailBench`](https://huggingface.co/datasets/microsoft/WebTailBench).
- A side-by-side V1↔V2 diff (task strings and rubric JSON) is
- hosted [here](https://microsoft.github.io/fara/docs/webtailbench_v1_v2_diff.html).
+* **2026-07-17** — **Fara-1.5 released!** A family of native computer use
+ agents at three scales (Fara1.5-4B, Fara1.5-9B, Fara1.5-27B) built on
+ Qwen3.5 and trained on data from the **FaraGen1.5** pipeline. Fara1.5-9B
+ reaches 63.4% on Online-Mind2Web and 86.6% on WebVoyager, a new state of
+ the art for its size class; Fara1.5-27B achieves 72.3% on Online-Mind2Web,
+ outperforming much larger proprietary systems. Read the
+ [paper](https://arxiv.org/abs/2606.20785) and the
+ [blog post](https://www.microsoft.com/en-us/research/articles/fara1-5-computer-use-agent/).
+* **2026-05-12** — **WebTailBench** is now a first-class benchmark in this
+ repo: the loader auto-downloads tasks and rubrics from
+ [`microsoft/WebTailBench`](https://huggingface.co/datasets/microsoft/WebTailBench)
+ (use the refreshed `test_v2` split; a V1↔V2 diff is hosted
+ [here](https://microsoft.github.io/fara/docs/webtailbench_v1_v2_diff.html)),
+ the **Universal Verifier** (`MMRubricAgent`) is the official judge, and the
+ reproducibility CLI lives in `webeval/scripts/webtailbench.py` (stand-alone
+ re-scoring via `webeval/scripts/verify_trajectories.py`).
* **2026-04-19** — Released **[CUAVerifierBench](https://huggingface.co/datasets/microsoft/CUAVerifierBench)**,
a human-annotated benchmark for evaluating CUA verifiers (i.e. judges that
score agent trajectories). Two splits — `fara7b_om2w_browserbase` (106
@@ -35,31 +43,22 @@
with per-judge UV-blind / UV-informed labels, Universal Verifier
outputs, and legacy verifier outputs side-by-side. The build script
that produced the dataset lives alongside the data on HuggingFace.
-* **2026-04-18** — Removed the `autogen-core` / `autogen-ext` dependency
- from `webeval`; chat completion clients are now self-contained under
- `webeval/src/webeval/oai_clients/`. No more autogen submodule install
- step; just `pip install -e .[vllm]` then `cd webeval; pip install -e .`.
-* **2026-04-18** — Incorporated WebTailBench (initial / now-stale
- version) directly into the repo as a first-class benchmark. The
- loader auto-downloads `WebTailBench-v1-rubrics.tsv` from
- [`microsoft/WebTailBench`](https://huggingface.co/datasets/microsoft/WebTailBench)
- and threads each task's published `precomputed_rubric` through to
- the verifier. Reproducibility CLI lives in `webeval/scripts/webtailbench.py`.
-* **2026-04-18** — Released the **Universal Verifier** (`MMRubricAgent`)
- as the official verifier for WebTailBench. Multimodal,
- rubric-grounded, two-model ensemble (`gpt-5.2` + `o4-mini`) with
- per-criterion scoring, outcome verification, and first-point-of-failure
- analysis. A stand-alone parallel runner is at
- `webeval/scripts/verify_trajectories.py` for re-scoring any directory
- of webeval trajectories without touching the solver.
---
## Overview
-**Fara-7B** is Microsoft's first **agentic small language model (SLM)** designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.
+**Fara-1.5** is a family of native Computer Use Agents (CUAs) at three scales — **Fara1.5-4B**, **Fara1.5-9B**, and **Fara1.5-27B** — built on Qwen3.5 and trained with supervised finetuning on data from **FaraGen1.5**, our scalable data pipeline of environments, solvers, and verifiers. Each model sets a new state of the art for its size class on browser-use benchmarks, and Fara1.5-27B outperforms much larger proprietary systems such as OpenAI Operator and Gemini 2.5 Computer Use on Online-Mind2Web.
+
+Fara-1.5 models operate through an observe-think-act loop: given a screenshot of the browser and the conversation history, the model reasons about the state of the task and outputs an action — mouse and keyboard inputs on directly predicted coordinates, web searches, or context management operations — with no accessibility trees or separate parsing models.
+
+