# smolagents Published articles for smolagents. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## DeepMath: A lightweight math reasoning Agent with smolagents DevFeed: [DeepMath: A lightweight math reasoning Agent with smolagents]() Original publisher: [Read original article]() Author: Daniel Fleischer; Moshe Berchansky; Moshe Wasserblat Published: 2025-12-04T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [smolagents](), [math](), [grpo](), [Fine-tuning](), [Python](), [Large Language Model](), [vllm](), [trl](), [datasets](), [Inference](), [Artificial Intelligence](), [Open Source]() Tags: [agents](), [artificial-intelligence](), [datasets](), [fine-tuning](), [grpo](), [inference](), [large-language-models-llms](), [llm](), [math](), [math-reasoning](), [open-source](), [python](), [reasoning](), [sandbox](), [smolagents](), [trl](), [vllm]() ### AI overview DeepMath is a lightweight math reasoning agent built on Qwen3-4B Thinking and implemented with smolagents. It uses GRPO fine-tuning to encourage concise Python snippets for deterministic computation, executes those snippets in a constrained sandbox, and reintegrates the results into the reasoning process. Evaluation on MATH500, AIME, HMMT, and HLE reports shorter outputs and often improved accuracy. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models DevFeed: [Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models]() Original publisher: [Read original article]() Author: Igor Margulis; Ofir Zafrir; Shira Guskin; Guy Boudoukh; Pedro Cuenca Published: 2025-09-29T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [qwen](), [AI Agent](), [Inference](), [intel](), [smolagents](), [GPU](), [Latency]() Tags: [ai-agent](), [gpu](), [guide](), [hub](), [inference](), [intel](), [latency](), [llm](), [models](), [nlp](), [qwen](), [smolagents]() ### AI overview The article explains how to accelerate the Qwen3-8B agent on an Intel Lunar Lake integrated GPU using OpenVINO.GenAI. Speculative decoding with Qwen3-0.6B as a draft model achieves about a 1.3x speedup, while pruning the draft model increases the speedup to about 1.4x. It also demonstrates running a fast, local AI agent with smolagents. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Jupyter Agents: training LLMs to reason with notebooks DevFeed: [Jupyter Agents: training LLMs to reason with notebooks]() Original publisher: [Read original article]() Author: Baptiste Colle; Hanna Yukhymenko; Leandro von Werra Published: 2025-09-10T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Jupyter Notebook](), [Data analysis](), [Data Science](), [LLMs](), [Fine-tuning](), [Open Source Models & Datasets](), [Benchmark](), [Human-AI evaluation](), [smolagents](), [qwen](), [ide]() Tags: [agents](), [analysis](), [benchmark](), [cursor](), [data](), [data-science](), [datasets](), [evaluation](), [fine-tuning](), [jupyter](), [llm](), [llms](), [qwen](), [research](), [smolagents]() ### AI overview The article presents Jupyter Agent, a system that executes code inside Jupyter notebooks to support data analysis and data science workflows. It describes a pipeline for generating training data, fine-tuning smaller models, and evaluating them on the DABStep benchmark, with examples involving Qwen models and smolagents. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## ScreenSuite - The most comprehensive evaluation suite for GUI Agents! DevFeed: [ScreenSuite - The most comprehensive evaluation suite for GUI Agents!]() Original publisher: [Read original article]() Author: Amir Mahla; Aymeric Roucher; Thomas Wolf Published: 2025-06-06T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [screensuite](), [gui-agents](), [computer-use](), [Benchmark](), [benchmarking](), [AI Chat](), [Claude]() Tags: [agents](), [artificial-intelligence](), [benchmarking](), [computer-use](), [docker](), [evaluation](), [gui](), [gui-agents](), [open-source](), [screensuite](), [smolagents](), [virtual-machines](), [vlm](), [vlms]() ### AI overview ScreenSuite is an open benchmarking and evaluation suite for GUI agents. It unifies 13 benchmarks covering perception, grounding, single-step actions, and multi-step agentic capabilities for Vision Language Models, with support for remote desktop sandboxes and Ubuntu or Android virtual machines launched in Docker. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## CodeAgents + Structure: A Better Way to Execute Actions DevFeed: [CodeAgents + Structure: A Better Way to Execute Actions]() Original publisher: [Read original article]() Author: Aksel Joonas Reedi; Aymeric Roucher Published: 2025-05-28T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Artificial Intelligence](), [AI Development](), [Code](), [Python](), [Large Language Model](), [gaia](), [JSON](), [Parsing]() Tags: [agents](), [ai](), [ai-agents](), [artificial-intelligence](), [code](), [coding](), [community](), [gaia](), [llm](), [nlp](), [open-source](), [python](), [smolagents](), [structured-generation](), [tools]() ### AI overview The article compares traditional JSON-based tool-calling agents with CodeAgents that generate executable Python. It explains that code-based actions provide more flexible tool composition, state management, loops, functions, conditionals, and hypothesis testing, while motivating structured generation to avoid errors when parsing code from Markdown. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Trace & Evaluate your Agent with Arize Phoenix DevFeed: [Trace & Evaluate your Agent with Arize Phoenix]() Original publisher: [Read original article]() Author: Sri Chavali; John Gilhuly; Aymeric Roucher Published: 2025-02-28T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [phoenix](), [agent observability](), [smolagents](), [OpenTelemetry](), [tracing](), [telemetry](), [Human-AI evaluation]() Tags: [agent](), [agents](), [debug](), [evaluation](), [free](), [hosting](), [hugging-face](), [instrumentation](), [opentelemetry](), [performance](), [phoenix](), [smolagents](), [telemetry](), [tracing](), [visualization]() ### AI overview This tutorial explains how to trace, evaluate, and debug a smolagents agent with Arize Phoenix. It demonstrates an agent powered by the Hugging Face Hub Serverless API that searches for Google share-price data from 2020 to 2024 and creates a line graph, then instruments the workflow with OpenTelemetry and OpenInference. Phoenix can run locally, as a self-hosted application, or on Hugging Face Spaces. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Open-source DeepResearch - Freeing our search agents DevFeed: [Open-source DeepResearch - Freeing our search agents]() Original publisher: [Read original article]() Author: Aymeric Roucher; Albert Villanova del Moral; merve; Thomas Wolf; Clémentine Fourrier Published: 2025-02-04T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Open Source](), [Artificial Intelligence](), [Large Language Model](), [gaia](), [smolagents](), [AI Development](), [AI Chat](), [OpenAI]() Tags: [agent](), [agentic](), [agents](), [ai](), [ai-assistants](), [artificial-intelligence](), [benchmark](), [llms](), [open-source](), [openai](), [research](), [smolagents]() ### AI overview This article describes an effort to reproduce OpenAI's Deep Research system and open-source the agentic framework behind it. It explains how an LLM-based framework can browse the web, read PDF documents, use tools, and organize actions into multiple steps, with performance evaluated using the GAIA benchmark. The article highlights smolagents and reports substantial performance improvements from adding an agentic framework, while noting that the work is still in progress. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## We now support VLMs in smolagents! DevFeed: [We now support VLMs in smolagents!]() Original publisher: [Read original article]() Author: Aymeric Roucher; merve; Albert Villanova del Moral Published: 2025-01-24T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [smolagents](), [Artificial Intelligence](), [AI Development](), [web browser](), [document ai]() Tags: [agentic](), [agents](), [artificial-intelligence](), [document-ai](), [multimodal](), [open-source](), [smolagents](), [vision](), [vlm](), [vlms](), [web-browser]() ### AI overview smolagents now supports vision-language models natively in agentic pipelines. The article explains how agents can receive images at initialization or dynamically through memory callbacks, enabling visual web browsing, Document AI workflows, and processing long PDFs with visual elements. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Introducing smolagents: simple agents that write actions in code. DevFeed: [Introducing smolagents: simple agents that write actions in code.]() Original publisher: [Read original article]() Author: Aymeric Roucher; merve; Thomas Wolf Published: 2024-12-31T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [smolagents](), [AI Development](), [Large Language Model](), [Code]() Tags: [agents](), [code](), [community](), [llm](), [nlp](), [open-source](), [smolagents](), [tool](), [tools](), [workflow]() ### AI overview Introducing smolagents, a lightweight approach for building AI agents whose language model outputs control application workflows and actions. The article explains agency as a spectrum, shows how multi-step agents use tools in a loop, and discusses when flexible agentic behavior is useful versus when deterministic workflows are more reliable. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Our Transformers Code Agent beats the GAIA benchmark 🏅 DevFeed: [Our Transformers Code Agent beats the GAIA benchmark 🏅]() Original publisher: [Read original article]() Author: Aymeric Roucher; Sergei Petrov Published: 2024-07-01T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [gaia](), [Benchmark](), [Transformers](), [smolagents](), [Large Language Model](), [Graphs](), [Retrieval-Augmented Generation]() Tags: [agent](), [agents](), [artificial-intelligence](), [benchmark](), [code](), [community](), [gaia](), [leaderboard](), [multimodal](), [nlp](), [research](), [retrieval-augmented-generation](), [smolagents](), [tool](), [tools](), [transformers]() ### AI overview The article presents a Transformers Code Agent that achieved top performance on the GAIA benchmark. It explains how LLM-based agents use tools and dynamically change their execution graph, and notes that the framework has since been upgraded to the standalone smolagents library. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## License to Call: Introducing Transformers Agents 2.0 DevFeed: [License to Call: Introducing Transformers Agents 2.0]() Original publisher: [Read original article]() Author: Aymeric Roucher; Lysandre; Pedro Cuenca Published: 2024-05-13T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [AI Bots]() Tags: [agents](), [artificial-intelligence](), [benchmark](), [framework](), [gpt](), [langchain](), [large-language-models-llms](), [llama3](), [llm](), [mixtral](), [nlp](), [smolagents](), [tools](), [transformers]() ### AI overview Hugging Face announces Transformers Agents 2.0, an LLM-driven agent framework focused on iterative agents, tool use, modularity, clarity, and sharing. The article also notes its transition to the standalone smolagents library. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science.