#agent-optimization

The latest AI and developer news about #agent-optimization, with the original source and a short summary.

AI21 Labs Releases Teel, an Open-Source Python Library for Parallelizing Agent IO

The library uses a shadow interpreter to parallelize independent IO-bound calls in sequential code without requiring async syntax, reducing runtime from 148s to 24s in benchmarks.

·3·2026.11.05 09:00

LangChain Optimizes Browser Use for Deep Agents with Stagehand, Cutting Costs by 13x

By adopting Stagehand's code mode and snapshot features, LangChain reduced per-task browser costs from $26.71 to $1.98 and improved success rates to 90% on WebVoyager.

·1·2026.11.04 01:00

ElevenLabs Launches ElevenAgents Architect to Automate Agent Improvement

ElevenLabs introduces ElevenAgents Architect, an AI expert that analyzes agent performance and proposes validated improvements, now available in Alpha.

·1·2026.10.06 21:00

AI Self-Improvement Benchmark Released

Scale AI has released HarnessOpt-Bench, a benchmark for measuring the self-improvement capabilities of AI agents.

·1·2026.08.28 05:00

Agent Lightning v1.0

Microsoft officially released Agent Lightning skill v1.0 to optimize AI agent performance.

·2026.08.25 02:00

Maestro Deep Research Agent

AI21 Maestro achieved SOTA on BrowseComp-Plus with 95.18% accuracy.

·2·2026.04.29 00:00