# AREX-2 arrives as an open deep-research agent model

> The reasoning-focused release pairs tool use with long context and self-improvement, and ships as a vision-language model on Hugging Face.

Published by The Open Weights on Sep 29, 2026. Canonical: https://theopenweights.com/news/arex-2-o62j

## Key facts

- Company: BAAI
- Model: AREX-2
- Version: 2
- Category: Reasoning
- Modalities: Reasoning, Vision-Language
- License: Other (Open weights, commercial use allowed)
- Context window: 262K tokens
- Architecture: Qwen3_5ForConditionalGeneration
- Precision: BF16
- Weights size: 54.7 GB
- Significance: notable
- Published: 2026-09-29
- Last verified: 2026-10-07
- Hugging Face: https://huggingface.co/BAAI/AREX-2
- Canonical URL: https://theopenweights.com/news/arex-2-o62j

A new model called **AREX-2** has appeared on Hugging Face, positioned as a "deep-research" agent built around reasoning, tool use, long context and what its authors describe as self-improvement. The release is hosted under the BAAI organization at [huggingface.co/BAAI/AREX-2](https://huggingface.co/BAAI/AREX-2) and is tagged for both reasoning and vision-language workloads.

The framing matters because "deep research" has become shorthand for a specific class of system: one that can plan a multi-step investigation, call external tools, and read long documents before producing an answer. Rather than a single-shot chat model, AREX-2 is pitched at that agentic workflow, where the model decides when to retrieve, compute, or verify.

## What the record tells us

- A reasoning-first model with vision-language (VLM) capabilities
- Designed for **tool use** and **long-context** tasks
- Described as supporting **self-improvement** in its research loop
- Published under an "other" license, so terms should be checked before use

Several specifics remain unstated at launch. The listing does not disclose a parameter count, context-window length, or benchmark results, and it is marked as a dense (non-MoE) model. Those details will determine how AREX-2 compares with the growing field of open agentic systems.

For now, the release is most useful as a signal of where open models are heading: away from standalone answer engines and toward configurable agents that combine reasoning, perception and tools. Teams interested in evaluating it should review the [model card](https://huggingface.co/BAAI/AREX-2) directly, particularly the license and any usage requirements, before building on top of it.

## Get the model

- [Hugging Face](https://huggingface.co/BAAI/AREX-2)

## Sources

- [BAAI/AREX-2](https://huggingface.co/BAAI/AREX-2) — Hugging Face, Sep 29, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "AREX-2 arrives as an open deep-research agent model", The Open Weights, Sep 29, 2026, https://theopenweights.com/news/arex-2-o62j