How do you convert real agent traces into reinforcement learning RL transitions to improve policy LLMs without changing your existing […]
Category: Open Source
OpenUK and UKRI collaborate on sustainable open source software for the UK public sector
OpenUK has announced plans to collaborate with UK Research and Innovation (UKRI) to shape new recommendations for sustainable software development […]
Liquid AI Releases LFM2-ColBERT-350M: A New Small Model that brings Late Interaction Retrieval to Multilingual and Cross-Lingual RAG
Can a compact late interaction retriever index once and deliver accurate cross lingual search with fast inference? Liquid AI released […]
MiniMax Releases MiniMax M2: A Mini Open Model Built for Max Coding and Agentic Workflows at 8% Claude Sonnet Price and ~2x Faster
Can an open source MoE truly power agentic coding workflows at a fraction of flagship model costs while sustaining long-horizon […]
Zhipu AI Releases ‘Glyph’: An AI Framework for Scaling the Context Length through Visual-Text Compression
Can we render long texts as images and use a VLM to achieve 3–4× token compression, preserving accuracy while scaling […]
Meet ‘kvcached’: A Machine Learning Library to Enable Virtualized, Elastic KV Cache for LLM Serving on Shared GPUs
Large language model serving often wastes GPU memory because engines pre-reserve large static KV cache regions per model, even when […]
PokeeResearch-7B: An Open 7B Deep-Research Agent Trained with Reinforcement Learning from AI Feedback (RLAIF) and a Robust Reasoning Scaffold
Pokee AI has open sourced PokeeResearch-7B, a 7B parameter deep research agent that executes full research loops, decomposes a query, […]
DeepSeek Just Released a 3B OCR Model: A 3B VLM Designed for High-Performance OCR and Structured Document Conversion
DeepSeek-AI released 3B DeepSeek-OCR, an end to end OCR and document parsing Vision-Language Model (VLM) system that compresses long text […]
Meet LangChain’s DeepAgents Library and a Practical Example to See How DeepAgents Actually Work in Action
While a basic Large Language Model (LLM) agent—one that repeatedly calls external tools—is easy to create, these agents often struggle […]
Kong Releases Volcano: A TypeScript, MCP-native SDK for Building Production Ready AI Agents with LLM Reasoning and Real-World actions
Kong has open-sourced Volcano, a TypeScript SDK that composes multi-step agent workflows across multiple LLM providers with native Model Context […]