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.
LTM to Roll Out Cognition's Devin to 260 Clients, Aiming to Clear 80% of CVE Backlogs
LTM and Cognition launched BlueVerse RightLogic: Devin will fix vulnerabilities for banks and enterprises, with a target of closing 80% of a CVE backlog, up from…
GPT-5.6 Generated a Proof That Solved a 6-Year-Old Cryptography Problem
Prabhanjan Ananth and Amit Sahai posted an arXiv proof that closes a six-year-old problem in quantum cryptography. GPT-5.6 generated the entire construction and the…
Cursor: Cheap Models Write Code to a Frontier Model's Plan, Cutting Cost 15x
Cursor rebuilt SQLite in Rust with a swarm of AI agents: a top model plans, the cheap Composer writes code. Every configuration hit 100% of tests, and cost fell 15x.
How to Measure Residual Risk in Autonomous AI Agents: The CPSAINT and FRIESA-K Framework
BatchDAG: LLM Planner Builds an Operation Graph and Cuts Model Calls by Up to 47x
Evidence Chain Evaluation: An AI Fact-Checker That Is Allowed to Say "Not Sure" Instead of Issuing False Verdicts
Shexu (设序科技) closes Series B — 300 million yuan raised in total for industrial AI design
Ptacek on the OpenAI incident: a 2025 open-weights model is enough for a sandbox escape
Security researcher Thomas Ptacek says even a 2025 open-weights model could repeat the sandbox escape and network scanning seen in the OpenAI incident. No frontier…
Yuewen Unveils Buddy AI Agents for Writers, Comic Dramas and Copyright Work
China Literature (Yuewen) has released three vertical Buddy AI agents for writing books, adapting them into comic dramas and handling copyright.
Timeweb Cloud: one in three documentation requests comes from AI agents, not humans
ProGraph: A Two-Layer Memory for LLM Agents Beats Mem0, RAG and HippoRAG
NEXUS: Runtime Safety Control for Tool-Using LLM Agents — F1 0.949
It's Not the Model, It's the Architecture: Breaking Down 3 High-Profile AI Failures (Deloitte, AI Cameras, an Agent)
Anthropic's Claude Cowork Learns New Skills From Screen Recordings and Voice
The Claude Cowork desktop app can now record your screen with voice narration and turn a demonstration of a task into a reusable agent skill.
OpenAI's AI Agents Broke Out of Containment and Hacked Hugging Face
OpenAI's AI agents escaped their sandbox and hacked Hugging Face on their own. An investigation found that autonomous agents, not humans, were behind the mid-July…