Retrieval-augmented generation (RAG) has been a game-changer for enterprise AI, and its evolution will help organizations save money, improve lives, and position themselves for the AI innovations still to come. Meet GraphRAG and agentic search: two powerful innovations pushing
AGENTS
-
Launch of Computer Use in smolagents with Qwen-VL grounding
By
–
We're launching Computer Use in smolagents! 🥳
— m_ric (@AymericRoucher) 6 mai 2025
-> As vision models become more capable, they become able to power complex agentic workflows. Especially Qwen-VL models, that support built-in grounding, i.e. ability to locate any element in an image by its coordinates, thus to… pic.twitter.com/mI8MuWZkISWe're launching Computer Use in smolagents! -> As vision models become more capable, they become able to power complex agentic workflows. Especially Qwen-VL models, that support built-in grounding, i.e. ability to locate any element in an image by its coordinates, thus to
-
Developers Embrace Gemini 2.5 Pro for High-Performance Tasks
By
–
Developers really like 2.5 Pro: “We found Gemini 2.5 Pro to be the best frontier model when it comes to "capability over latency" ratio. I look forward to rolling it out on Replit Agent whenever a latency-sensitive task needs to be accomplished with a high degree of
-
Meta-Agentic: Self-Evolving Agent Factory Revolutionizes AGI Development
By
–
Meta-Agentic 👁️✨ — the master key 🗝️
— MONTREAL.AI (@Montreal_AI) 6 mai 2025
A self-evolving agent-factory that spins exponential design loops, harvests value across every vertical, and rewrites the rulebook as it learns.
Demo: https://t.co/YtFeoMMiT3
Own the future.#AGI #AGIALPHA #MetaAgentic pic.twitter.com/V2QC6sTkwBMeta-Agentic — the master key A self-evolving agent-factory that spins exponential design loops, harvests value across every vertical, and rewrites the rulebook as it learns. Demo: https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/meta_agentic_agi
… Own the future. #AGI #AGIALPHA #MetaAgentic -
AI Agent System Automates Scientific Discovery and Lab Synthesis
By
–
Des agents IA scientifiques peuvent automatiser les découvertes, depuis les idées de recherche jusqu’aux expériences en laboratoire ! Nous montrons qu’un système d’agents (LLMs, modèles de diffusion, équipements matériels) a été capable de découvrir et de synthétiser 5 nouvelles
-
Fellou AI as an indefatigable digital worker
By
–
Fellou feels like the AI version of an intern who never sleeps
-
Policy Patchwork Quilts: Complex Systems in Food Assistance
By
–
For a longer discussion on how we end up with patchwork quilts in policy, see Complex Systems with Dave Guarino. He used to work on CalFresh, and got a brisk tour of let’s-feed-the-people ecosystems, and where the cracks are between them.
-
OpenAI Acquires Windsurf, Cursor Valued at $9 Billion
By
–
OpenAI achète Windsurf pour 3 milliards de dollars. Cursor reçoit un nouvel investissement de 900 millions de dollars et est valorisé à 9 milliards. C'est très clair : le marché voit l'avenir dans les agents de codage / éditeurs IA. Les modèles deviennent de plus en plus
-
Survey of Agent Interoperability Protocols: MCP, ACP, A2A, ANP
By
–
Another survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP). Link: https://
arxiv.org/pdf/2505.02279 -
Meta-Agentic: Second-Order Agency in AI Systems
By
–
Definition – "Meta-Agentic" Meta-Agentic (adj.) Pertaining to an agent whose primary function is to create, select, evaluate or re-configure other agents and the interaction rules between them, thereby exercising second-order agency over a population of first-order agents. The