Good point! Trust and traceability are still big gaps in agent systems.
AGENTS
-
Runway Characters: Create Custom AI Assistants for Learning
By
–
Learn a new language. Discuss the nature of thought. Or, just figure out why your plants keep giving up on you.
— Runway (@runwayml) 10 mars 2026
Try Runway Characters today directly inside the web app. Explore preset Characters. Or, create your own.https://t.co/8P77A3Tq3K https://t.co/ZBPy0YFRCVLearn a new language. Discuss the nature of thought. Or, just figure out why your plants keep giving up on you. Try Runway Characters today directly inside the web app. Explore preset Characters. Or, create your own. http://
app.runwayml.com/characters -
Introducing arXivQA: Training retrieval agents for arXiv search
By
–
Introducing arXivQA: Training retrieval agents for arXiv search We curate a multi-hop arXiv dataset based on real queries and use rubric-as-rewards to train a Qwen model for production-grade retrieval Our latest blog details our experience training with both RLVR and rubrics
-
Karpathy’s AutoResearch Enables AI Self-Improvement Loop
By
–
You can now give an AI a GPU and let it improve its own model overnight. This repo turns LLM research into an automated search loop. @karpathy just open-sourced a system that lets AI iterate on its own training code. Karpathy’s AutoResearch turns LLM improvement into an
-
NVIDIA Scales Agent Inference with Engineering Stack Innovation
By
–
NVIDIA's AI Engineers: Agent Inference at Scale and "Speed of Light" https://
latent.space/p/nvidia-brev-
dynamo
… @nvidia is embracing Engineers at all levels of the stack: from the sublime DX of @brevdev
, to the open source datacenter framework of Dynamo. @KranenKyle and @NaderLikeLadder join -
Agent-to-Agent Communication: The New AI Frontier
By
–
The tide is turning. The focus is now agent-to-agent communication.
-
Self-Evolving AI Agents Tool Genesis Benchmark Research
By
–
New research on Self-Evolving AI Agents. Really interesting benchmark for evaluating a critical but overlooked capability: can LLMs create reusable tools from scratch, not just use existing ones? Tool-Genesis tests whether models can infer interfaces, generate schemas, and
-
Portfolio Strategy: Specialized Models Beat One-Size-Fits-All
By
–
The winning strategy is not one model to rule them all. It’s a portfolio: • reasoning models
• fast models
• research models
• coding agents
• multimodal systems
A model for every job. -
Enterprise AI Agents Growing Rapidly, Security Governance Lagging Behind
By
–
Gartner: 40% of enterprise apps will have built-in AI agents by end of 2026. That's up from less than 5% today. Most CISOs are not ready for this. Organisations are deploying agents faster than they can secure them. Speed is fine. Governance catching up would be better. #AIAgents
→ View original post on X — @svenphilipsen, 2026-03-10 14:00 UTC
-
Free AI Agents Course: Learn Text and Audio Models
By
–
Excited to announce our first text + audio AI course. Searching for a solid entry point to learn about AI agents? Look no further. FREE for everyone. Enroll now!