Self-Evolving AI Agents are about to blow up 🚀🔥 New Survey Alert 🚨 From static LLMs ➡️ lifelong, adaptive agents 🌱🤖 A Comprehensive Survey of Self-Evolving AI Agents... — your roadmap to the future of AI that learns & evolves after deployment! 💡 https://t.co/TBYfLLdaD1

queuing for the registration .. #EMNLP2025

The HowOne AI team is thrilled to be at #EMNLP2025 in Suzhou @emnlpmeeting ! We’re showcasing how one person can build a fully functional & self-evolving Agentic AI App — from frontend to backend to workflow — using just a natural language prompt. No coding. No drag & drop.

Heading to Suzhou for @emnlpmeeting . This time, I am with different roles, and will be excited to discuss with more old and new friends. Come by our work presentations and chat with us 🤝#EMNLP2025

Many people ask me what AI tools to use. I'll always suggest stopping learning how to use AI tools. 🤖 AI Agents already do it better than you. Instead, learn how to collaborate with them. That’s the real skill of the future. #AIAgent #HowOne

🚀 HowOne = One Prompt → Real Multi-Modal App I built an image editing app that: 🖼 Accepts image uploads 💬 Takes natural language prompts 🎨 Edits images instantly — here, a side-facing cartoon turned front-facing. Multi-modal input, fully functional UI, backend & agentic

It has now received 2k ⭐️ stars on GitHub!🎉 The next generation of AI Agents should be self-evolving!🍀

📸 New Preprint Out! If you already have a SOTA Radiology MLLM, why bother training it again? Especially when new data are scarce and GPUs are even scarcer - that's a frustrating dilemma. 🚀 We introduce a training-free and retrieval-free inference framework that boosts

Our survey paper’s GitHub repo just hit ⭐️1K stars! 🚀🎉 ---> https://t.co/6xZchrT0EY

LLM Agent = LLM + Planning + Reasoning + Tool + Memory + Action + Perception + Self-improve --- That's a much better formulation for LLM Agents.

Guibin's talk will be happening in five minutes. Please come and join the discussion with Guibin.

🚀 EvoAgentX Talk – From LLM to Automated Agents: The Power of Agentic RL, join us this Sunday! 📅 Date & Time: Sep 28 2025, Sunday, 4:30 PM (Beijing Time) 🔗 Join Here: Zoom Link https://t.co/jhvDiKwbuT or Meeting ID: 862 8273 5663, Passcode: 396325 🎙️ Session Overview

✨ EvoAgentX Community Call — this Sunday! ✨ We’re excited to invite you to our official open-source community meeting 🕒 When: Sunday, 9:30 AM (UK time) 📍 Where: Zoom ID: 862 8273 5663 Passcode: 396325 Over the past months, we’ve been working hard to evolve EvoAgentX from

🚀 Revolutionizing Multimodal Knowledge Management: EvoAgentX makes AI go beyond text! https://t.co/uaShEFQrWI Want your agents to see images, read text, and answer questions with both? Our multimodal RAG workflow makes it real. Workflow Overview Our example demonstrates the

Hello X! 🚀 EvoAgentX v0.1.0 is live — and it redefines how agentic AI gets built, optimized, and shipped. Stop hand-wiring brittle pipelines. With EvoAgentX, agents build themselves from a single goal, then evaluate and evolve to keep getting better. * What’s inside v0.1.0 :

🚀 Excited to share that EvoAgentX, the world’s 1st open-source self-evolving framework for AI Agents, has been accepted at EMNLP 2025 (Demo Track)! It now received ⭐ 1.4k stars on GitHub: https://t.co/XrvxxjVwp4 🎉 We’ll be presenting it in Suzhou. @EvoAgentX

Thanks for sharing @omarsar0 . Check out the paper here: https://t.co/IlvSQAwsSa , and explore more in this curated list of essential papers on Self-Evolving AI Agents: https://t.co/6xZchrSsPq 🚀 The list will be continuously updated and maintained! @EvoAgentX

My past grant proposals have turned into reality so quickly — just one year! Can’t imagine what the next five years will bring. 🚀 https://t.co/RsnU9rppK6 https://t.co/dp3fxPOdei --> @EvoAgentX

✨ Our survey GitHub repo hit 500+ stars in only 2 weeks🚀! Grateful for all the support 🌟!

⭐️ Star this repo and access a handpicked list of essential papers on Self-evolving AI Agents:

3 out of 4 papers accepted at @emnlpmeeting #EMNLP2025 🎉 Congrats to @XinhaoYi, Zhaohan Meng, @Auss_Abbood, and all the others coauthors! The remaining one ( https://t.co/s60VSTWqJd) wasn’t accepted this time, but it’s still a strong piece of work, and is included in @EvoAgentX!