Aymeric Roucher PRO

m-ric

https://m-ric.com

AI & ML interests

Used to work at Hugging Face 🤗

Recent Activity

published a dataset 5 days ago

m-ric/predibench-dump

updated a dataset 5 days ago

m-ric/predibench-dump

upvoted a paper 5 days ago

MuPT: A Generative Symbolic Music Pretrained Transformer

View all activity

Organizations

published an article 8 months ago

Article

PrediBench: Testing AI models on prediction markets

charles-azam

•

Sep 24, 2025

• 5

published an article 10 months ago

Article

ScreenEnv: Deploy your full stack Desktop Agent

A-Mahla, m-ric

•

Jul 10, 2025

• 76

published an article 10 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf

•

Jul 8, 2025

• 773

published an article 11 months ago

Article

ScreenSuite - The most comprehensive evaluation suite for GUI Agents!

A-Mahla, m-ric, thomwolf

•

Jun 6, 2025

• 56

published an article 12 months ago

Article

CodeAgents + Structure: A Better Way to Execute Actions

akseljoonas, m-ric

•

May 28, 2025

• 82

published an article about 1 year ago

Article

Trace & Evaluate your Agent with Arize Phoenix

schavalii, jgilhuly16, m-ric

•

Feb 28, 2025

• 41

published an article over 1 year ago

Article

Open-source DeepResearch – Freeing our search agents

m-ric, albertvillanova, merve, thomwolf, clefourrier

•

Feb 4, 2025

• 1.32k

published an article over 1 year ago

Article

DABStep: Data Agent Benchmark for Multi-step Reasoning

eggie5, martinigoyanes, frisokingma, andreumora, lvwerra, thomwolf, m-ric

•

Feb 4, 2025

• 128

published an article over 1 year ago

Article

Anthropic CEO: is DeepSeek-R1 a revolution in AI?

m-ric

•

Jan 30, 2025

• 6

published an article over 1 year ago

Article

We now support VLMs in smolagents!

m-ric, merve, albertvillanova

•

Jan 24, 2025

• 113

published an article over 1 year ago

Article

Introducing smolagents: simple agents that write actions in code.

m-ric, merve, thomwolf

•

Dec 31, 2024

• 1.19k

published an article over 1 year ago

Article

Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge

Vinsingh, rajgreen, m-ric

•

Oct 28, 2024

• 29

published an article over 1 year ago

Article

Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge

Vinsingh, rajgreen, m-ric

•

Oct 28, 2024

• 29

published an article almost 2 years ago

Article

Our Transformers Code Agent beats the GAIA benchmark 🏅

m-ric, sergeipetrov

•

Jul 1, 2024

• 100

published an article almost 2 years ago

Article

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

m-ric

•

Jun 20, 2024

• 26

published an article almost 2 years ago

Article

CodeAgents + Structure: A Better Way to Execute Actions

akseljoonas, m-ric

•

May 28, 2025

• 82

published an article almost 2 years ago

Article

License to Call: Introducing Transformers Agents 2.0

m-ric, lysandre, pcuenq

•

May 13, 2024

• 137

published an article over 2 years ago

Article

Open-source LLMs as LangChain Agents

m-ric, Jofthomas, andrewrreed

•

Jan 24, 2024

• 78

published an article over 2 years ago

Article

Open-source LLMs as LangChain Agents

m-ric, Jofthomas, andrewrreed

•

Jan 24, 2024

• 78

Aymeric Roucher PRO

AI & ML interests

Recent Activity

Organizations

m-ric's activity

PrediBench: Testing AI models on prediction markets

ScreenEnv: Deploy your full stack Desktop Agent

SmolLM3: smol, multilingual, long-context reasoner

ScreenSuite - The most comprehensive evaluation suite for GUI Agents!

CodeAgents + Structure: A Better Way to Execute Actions

Trace & Evaluate your Agent with Arize Phoenix

Open-source DeepResearch – Freeing our search agents

DABStep: Data Agent Benchmark for Multi-step Reasoning

Anthropic CEO: is DeepSeek-R1 a revolution in AI?

We now support VLMs in smolagents!

Introducing smolagents: simple agents that write actions in code.

Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge

Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge

Our Transformers Code Agent beats the GAIA benchmark 🏅

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

CodeAgents + Structure: A Better Way to Execute Actions

License to Call: Introducing Transformers Agents 2.0

Open-source LLMs as LangChain Agents

Open-source LLMs as LangChain Agents