Autonomous Memory Management in LLM Agents LLM agents struggle with long-horizon tasks due to context bloat. As interaction history grows, computational costs explode, latency increases, and reasoning degrades from distraction by irrelevant past errors. The standard approach
AGENTS
-
Open-Weight Models Build CLI Runner Autonomously Without Human Intervention
By
–
Open-weight models just built a 20-feature CLI runner autonomously! Kilo Code tested MiniMax M2.1 and GLM 4.7 by having them build a complete CLI task runner from scratch. Both models succeeded. No human intervention for 10-14 minutes straight. The test was realistic: build a
-
HuggingChat Reading Assistant: Usage Feedback and Improvements
By
–
> has a HuggingChat reading assistant so you can ask questions without leaving the page that's great! do you use it a lot so far? Any way we can improve it? cc @mishig25
-
OpenSearch Agentic Memory: Building Context-Aware Agents
By
–
OpenSearch as an agentic memory solution: Building context-aware agents using persistent memory https://
buff.ly/OtZ3ZMe
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Open-Source Coding Agents Meeting Highlights Community
By
–
Was fun to meet @thdxr @opencode today. Let’s go open-source coding agents!
-
GPT-5.2 Writes 3M Lines of Code to Build Browser in Cursor
By
–
Truly incredible how fast the frontier of agentic coding is moving GPT-5.2 wrote 3M+ lines of code, nonstop for three days, to build a browser from scratch in Cursor!
-
Gemini Personal Intelligence: AI Understanding User Data Securely
By
–
For AI to be truly useful, it needs to understand you.
— Demis Hassabis (@demishassabis) 14 janvier 2026
With Personal Intelligence, we’re beginning to solve this. With your permission, Gemini can now securely reason across your own data to answer questions that generic models simply can't – like suggesting plans based on… https://t.co/jMTGTt3MO0For AI to be truly useful, it needs to understand you. With Personal Intelligence, we’re beginning to solve this. With your permission, Gemini can now securely reason across your own data to answer questions that generic models simply can't – like suggesting plans based on
-
Google Gemini Personal Intelligence: Hyper-Personalized AI Assistant
By
–
Announcing Personal Intelligence, a more personalized @GeminiApp designed just for you.
— Google AI (@GoogleAI) 14 janvier 2026
How it works:
— Customized: With your permission, it reasons across your @Gmail, @YouTube, @GooglePhotos, and Search apps to share hyper-relevant and context-aware responses
— Secure: If… pic.twitter.com/9Y8pfS46deAnnouncing Personal Intelligence, a more personalized @GeminiApp designed just for you. How it works:
— Customized: With your permission, it reasons across your @Gmail
, @YouTube
, @GooglePhotos
, and Search apps to share hyper-relevant and context-aware responses
— Secure: If -
New Document AI Course: OCR to Agentic Document Extraction
By
–
New course: Document AI: From OCR to Agentic Doc Extraction, built with @LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp.
— Andrew Ng (@AndrewYNg) 14 janvier 2026
Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic… pic.twitter.com/dG9SwmFgKqNew course: Document AI: From OCR to Agentic Doc Extraction, built with @LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually — as images — to parse information and extract fields. Skills you'll gain: – Build agents to convert unstructured files into structured Markdown/HTML and JSON – Use ADE to parse complex data like forms, handwriting, or equations – Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation – Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently: deeplearning.ai/short-course…
→ View original post on X — @andrewyng, 2026-01-14 17:42 UTC
-
Agentic Hackathon Showcases Impressive AI Agent Projects
By
–
Super impressed by the projects at the Agentic Hackathon last weekend! Many teams work on really hard/important problems: * Long running tasks: memory management, recovering from mid-task failures, and maintaining consistency across steps and sub-agents * Adaptive retrieval from multiple sources: databases, search indices, and websites * Agents that work with voice, video, and even 3D environments If you are in SF, come check out the finalist demos tomorrow! luma.com/6bd4bt9j There will be talks by Douglas Eck, who is doing amazing work with Veo and Imagen and many other awesome folks. Thanks @MongoDB and @cerebral_valley for hosting and for letting me serve as a judge for these fantastic projects.