<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/sources/huggingface/best-of/2025/09" -->

---
title: Best Hugging Face posts — September 2025 | daily.dev
description: The most upvoted Hugging Face posts from September 2025, curated by the daily.dev community.
canonical: https://daily.dev/sources/huggingface/best-of/2025/09
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:url: https://daily.dev/sources/huggingface/best-of/2025/09
og:type: website
og:site_name: daily.dev
og:title: Best Hugging Face posts — September 2025 | daily.dev
og:description: The most upvoted Hugging Face posts from September 2025, curated by the daily.dev community.
og:image: https://media.daily.dev/image/upload/s--VAY5ToZt--/f_auto/v1724209435/public/daily.dev%20-%20open%20graph
---

# Best of Hugging Face — September 2025

1. 1  
[](https://daily.dev/posts/jupyter-agents-training-llms-to-reason-with-notebooks-asgc1qnbf "Jupyter Agents: training LLMs to reason with notebooks")  
Article  
![Avatar of huggingface](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1)Hugging Face·51w  
Jupyter Agents: training LLMs to reason with notebooks  
Hugging Face developed Jupyter Agent, a system that trains small language models to perform data science tasks by executing code in Jupyter notebooks. They created a comprehensive pipeline starting with 2TB of Kaggle notebooks, applied deduplication and quality filtering, generated synthetic question-answer pairs, and fine-tuned Qwen3-4B models. The approach achieved 75% accuracy on easy DABStep benchmark tasks, demonstrating that smaller models can become effective data science agents with proper training data and scaffolding. The project includes open-source datasets, trained models, and a simplified 200-line scaffolding system.  
28
2. 2  
[](https://daily.dev/posts/gaia2-and-are-empowering-the-community-to-study-agents-kxi9agjkn "Gaia2 and ARE: Empowering the community to study agents")  
Article  
![Avatar of huggingface](https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1)Hugging Face·50w  
Gaia2 and ARE: Empowering the community to study agents  
Hugging Face introduces Gaia2, an advanced AI agent benchmark that goes beyond read-only tasks to evaluate interactive behaviors in real-world conditions. Unlike its predecessor GAIA, Gaia2 tests agents on complex scenarios including ambiguity handling, time-sensitive actions, and noise tolerance using a smartphone mock-up environment. The release includes the open-source Agent Research Environments (ARE) framework for running, debugging, and evaluating agents with structured trace recording. Current results show GPT-5 as the top performer, while temporal reasoning remains challenging for all models. The platform enables researchers to create custom scenarios and connect their own tools via MCP integration.  
24

[See all Hugging Face archives](/sources/huggingface/best-of)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@graph":[{"@type":"CollectionPage","@id":"https://daily.dev/sources/huggingface/best-of/2025/09#page","url":"https://daily.dev/sources/huggingface/best-of/2025/09","name":"Best Hugging Face Posts — September 2025","description":"The most upvoted Hugging Face posts from September 2025, curated by the daily.dev community.","isPartOf":{"@type":"WebSite","url":"https://daily.dev"}},{"@type":"ItemList","@id":"https://daily.dev/sources/huggingface/best-of/2025/09#items","numberOfItems":2,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/posts/jupyter-agents-training-llms-to-reason-with-notebooks-asgc1qnbf","name":"Jupyter Agents: training LLMs to reason with notebooks"},{"@type":"ListItem","position":2,"url":"https://daily.dev/posts/gaia2-and-are-empowering-the-community-to-study-agents-kxi9agjkn","name":"Gaia2 and ARE: Empowering the community to study agents"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Sources","item":"https://daily.dev/sources"},{"@type":"ListItem","position":3,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":4,"name":"Best of","item":"https://daily.dev/sources/huggingface/best-of"},{"@type":"ListItem","position":5,"name":"September 2025"}]}]}
```

