Arthur Kakande

Tutorial: Building your first ReAct Agent from Scratch Building your first sales assistant agent that can ReAct (Reason + Act) seamlessly during task execution.

Let's combine reasoning and action in LLMs for more reliable #AI systems. My latest blog explains how to build ReAct agents from scratch—step by step!

👉🏽 pub.towardsai.net/tutorial-bui...

#LLMs #ReAct #NLP #TechBlog #Agents #MachineLearning

ReAct: Synergizing Reasoning and Acting in Language Models While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-though...

LLMs excel in language understanding and decision-making, but their reasoning and action abilities are studied separately. This paper introduces ReAct, a novel approach where LLMs merge reasoning and task-specific actions, enhancing synergy between thought and execution.
#AI
arxiv.org/abs/2210.03629

Understanding Reinforcement Learning and Multi-Agent Systems: A Beginner’s Guide to MARL (Part 1) When we learn from labeled data, we call it supervised learning. When we learn by grouping similar items, we call it clustering. When we…

Ever wondered how machines learn to make decisions in complex, dynamic environments? Or how multiple #AI agents can work together? In my latest blog, I break down the fascinating world of #RL & #MARL in an easy-to-understand way.

👉🏽 pub.towardsai.net/understandin...

#DistributedAI #DataScience

Call for Workshops & Tutorials – SEMANTiCS 2025
📍 Vienna, Austria | Sept 3-5, 2025
🗓️ WS Deadline: Mar 22
🗓️ Tutorials Deadline: Jun 11
More info on the website: 2025-eu.semantics.cc/page/cfp_ws
Submit via EasyChair: easychair.org/conferences/...
#SemanticsConf #LinkedData #SemanticWeb #AI

The paper discusses a novel approach to converting #SemanticWeb Services into formal PDDL descriptions. This conversion enables automated planning and scheduling in Industry 4.0 environments, particularly in smart manufacturing systems.
👉🏽 www.wi2.uni-trier.de/shared/publi...

#AI #Automation

ShinyConf 2025 Registration and Call for Proposals are open! - Posit Join us for ShinyConf 2025, the biggest virtual Shiny event of the year hosted by our partner Appsilon!

ShinyConf 2025! Develop Shiny apps? Submit a proposal by Feb 2nd! Free virtual conf (April 9-11) with workshops, talks & app showcases. Learn more & register: posit.co/blog/shinyco...

#rstats #pydata #RShiny #ShinyforPython

YouTube video by HuggingFace Hugging Face Journal Club - DeepSeek R1

"let's figure out how to make this work in real life"😂 www.youtube.com/watch?v=1xDV...

#DeepSeek #AI #RL

🔵AVAILABLE NOW: Multiagent Reinforcement Learning Course

This course, organised by the IIIA, was given by
Stefano V. Albrecht last September. We hope you find it useful and that you can enjoy and learn as much as we did.

▶️Playlist course: youtube.com/playlist?lis...

NVIDIA Unveils ‘Mega’ Omniverse Blueprint for Building Industrial Robot Fleet Digital Twins According to Gartner, the worldwide end-user spending on all IT products for 2024 was $5 trillion. This industry is built on a computing fabric of electrons, is fully software-defined, accelerated — a...

New framework enables next era of industrial #AI and robot #simulation through software-defined testing and optimization to factories and warehouses.

#DigitalTwins #AutonomousSystems
blogs.nvidia.com/blog/mega-om...

🤖🍔Burger Generator ✨
This app simulates burger, sandwich & wrap assembly using CBR for smart planning & RPA for smooth prep. Missing an ingredient? It suggests clever swaps based on past cases. Watch your snack assemble step by step!

Try it here 👉🏽 burgergenerator.streamlit.app

#AI #Robotics #Tech

GitHub - unslothai/unsloth: Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory - unslothai/unsloth

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

#LLMs #AI

GitHub 👉🏽 github.com/unslothai/un...

Check out an FAQ bot built with #Intellikit and #Streamlit that uses Conversational Case-Based Reasoning (#CBR) to provide more accurate, context-aware answers. Unlike standard bots, it recalls similar past interactions to better address user queries.

Try the demo👉🏽
faqsbot.streamlit.app

GitHub - docusealco/docuseal: Open source DocuSign alternative. Create, fill, and sign digital documents ✍️ Open source DocuSign alternative. Create, fill, and sign digital documents ✍️ - docusealco/docuseal

Open source DocuSign alternative. Create, fill, and sign digital documents

github.com/docusealco/d...

#OpenSource

R in Production, r-in-production.org, is a new book that will help you put R into production, coupled with (in the near future) new tools to make the process less painful. I'm working on this with @thomasp85.com , @gaborcsardi.bsky.social, and @hfrick.bsky.social.