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.
BigSleep LLM Agent Finds 45 V8 Vulnerabilities, Fuzzilli 37, With 25% Overlap
Project Zero compared the BigSleep LLM agent and the Fuzzilli fuzzer on V8 over six months: 45 vulnerabilities vs 37. Overlap: a quarter in the tracker, about 60%…
AWS Launches Multi-Turn RL in SageMaker: gpt-oss-20b Climbs From 15% to 69% for $339
SageMaker AI now fine-tunes agents on a single reward for an entire chain of steps. On Wordle, gpt-oss-20b rose from 61% to 84% of words solved; training tokens…
Microsoft and Hugging Face trained Qwen3.8-27B on database-state rewards: from 38 to 107 tasks
Database end-state checks became the reward for GRPO: in 50 steps, Qwen3.8-27B lifted pass@1 from 51.70% to 60.78% and nearly tripled its count of 20/20 tasks.
2026 Open-Source Models Claim 1M Context but Read It Selectively
Who Wins the Instruction Conflict: Position, Chat Role, or Just a Label?
Memory Compaction in AI Agents Wipes Out Up to a Third of Task Rules — and Benchmarks Don't Notice
Retell Grows to 100 Million Calls a Month on OpenAI Models and Codex
An Agent Builds a Motion Studio From 20 Open-Source Libraries, From Remotion to Whisper
Remotion, Three.js, Rapier, Chatterbox and faster-whisper: 20 ordinary JS and Python libraries that let a coding agent turn a brief into animation, voiceover…
Cline Pushes an Open Model to 11,840 Tokens per Second on a Single GPU
The Cline team took a single NVIDIA GPU, an open model, and a handful of experiments to nearly triple text-generation throughput — from 6,058 to 11,840 tokens per…
METR and Redwood Broke OpenAI's Agent Monitoring: 75–94% of Traffic Covered
ElevenLabs Launches Eleven Realtime: A Voice Agent in a Single Model, 98.8% on Big Bench Audio
OpenAI details how its FDE team works: 90% of custom code gave way to Codex skills
Anthropic finds experts follow an AI agent's lead in 86% of contested choices
ElevenLabs Hands Its Support Desk to an AI Agent: 22,000 Tickets a Month, 65% Without Humans
ElevenLabs runs its own support on ElevenAgents: the agent fully resolves 65% of requests, replies in 60 seconds, and 70% of its conversations get positive ratings.
Anthropic Advises Cutting Half Your Subagents: One Loop Ran Twice as Fast
Anthropic's Applied AI team reviewed enterprise deployments: a single agent with skills often beats a multi-agent harness on quality, cost and speed. One client saw…