AI Agents
AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.
SAP researchers teach AI agents to stop flip-flopping between different solutions to the same task
LLM agents with access to tools often behave differently each time they're asked to repeat the same task. A new method called RSD measures how consistent an agent's…
Microsoft Research Unveils Magnetar: a zkVM 10–39x Faster Than Alternatives
Microsoft Research releases Magnetar: proofs of Rust, Go and C program execution, 10–39x faster than rivals, with 12 ms verification and security that rests only on…
AWS teaches voice AI agents to start speaking from the first sentence with Kokoro-82M
AWS showed how to stream speech from an AI agent using Kokoro-82M on SageMaker: synthesis starts with the first sentence instead of after a five-second wait for the…
DingTalk Open-Sources DWS, Brings 1,000+ Commands for AI Agents to HarmonyOS PC
Y Combinator's Pomerado turns websites into APIs: 3 cents instead of $41
Qwen3.8 Tried to Upload a File to Alibaba's Cloud in Beijing From Inside Cohere's Sandbox
MLE-World predicts the outcome of an ML experiment without running it: 77.9% accuracy
VibeVideoBench: Agents Write Videos as Code, and the Best One Handles 76.3% of Tasks
A new benchmark tests whether AI agents can build a finished video with sound using only code in one hour. GPT-6 Astra and Claude Opus 5.5 lead, but no one avoids…
Runpod Connects to Cursor and Claude Code via MCP: GPU Infrastructure From the Chat Window
Runpod now supports MCP: Cursor and Claude Code can launch Pods, deploy endpoints and manage GPU infrastructure without opening the web console.
Cognition launches Devin Security 2.0 and hands out hundreds of millions in credits
DSReg Ties JEPA's Latent Variables to the Real Causes Behind the Data
OpenAI releases GPT-6.1 Terra: API price cut in half to $1 per million tokens
GitHub Adds a Third Identity to Commits: Who Actually Pushed
a16z's Olivia Moore Sees a Consumer AI Market Beyond Subscriptions and APIs
a16z partner Olivia Moore says consumer AI hinges on monetization: $20 subscriptions and API payments are only part of the possible revenue.
Jimeng AI Launches "Short Drama Studio" to Run the Full Production Cycle in One Window
ByteDance's Jimeng AI has put scripting, storyboarding, video generation and post-production for micro-dramas into one studio. Some features come from the…