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.
Lean Compilation Overstates Formalization Accuracy by Up to 29.5 Points
An agent with Lean tools compiles 87.2% of statements, but only 57.7% are judged correct. The benchmark authors measured how much compilation overestimates…
Researchers Test 16 Types of Hints for OPSD and Find a Selection Metric
16 privileged-information configs, 3 agentic benchmarks, 3 models: KL metrics predict how much a hint will help OPSD better than directly testing the hint's…
8B-Parameter Model Beats Claude Opus 4.8 at Generating Scientific Ideas
Salesforce researchers trained an 8B model with set-level reinforcement learning to generate diverse scientific ideas. On a contamination-free benchmark, it…
Lovable launches Deploy on Azure: your apps and data live in your own subscription
Google Antigravity Finds an Antimicrobial Peptide Candidate in a 97-Amino-Acid Protein
MOSS-Image: Open 5B Model Renders Long Text with 96.3% Coverage
MIST shows video world models don't forget; they fail to carry out the command
Vercel Shop Reaches GA: Shopify Storefronts Learn to Sell to AI Agents
Vercel and Shopify launched an open-source Next.js storefront template that gives agents machine-readable product pages and the UCP protocol. PAIGE case: +22%…
OpenAI's Interpretability Founder Says 90% of Neurons Have a Single Function
OpenAI's Nick Cammarata argues that with agentic tools even a trillion-parameter model is nearly readable, and 90% of neurons serve one function. The essay is…
An LMS and CRM at 205,000 Lines of Code, Built by AI Agents: The Real Cost of Running It, Three Lead States, and One \r Character
Researchers Propose Anti-Persistence: LLM Agent Memory Without Stored Rules
TokenWorth Teaches AI Agents to Forget: Best Results on Three Environments With the Fewest Tokens
RIDAR catches integrity violations by AI scientists: 3964 cases across 300 runs
Cognition releases agent plugin to fix PHP and Node.js holes, including a CVSS 9.2 flaw
After the critical PHP2Shell flaws and a Node.js release fixing 10 CVEs, Cognition open-sourced a plugin that has Devin and other coding agents find and patch…
HiSTEVE 1.0 Plays Minecraft With a Mouse and Keyboard: 85.0% on MineStudio Bench
VLA agent HiSTEVE 1.0 completes long Minecraft tasks with no API and no hidden game state: 85.0% on MineStudio Bench, 37.4% on OpenHA, and an iron pickaxe from…