📄 文章列表

8 篇文章
VentureBeat

Researchers made AI agents better by turning academic papers into working code — no retraining required

✅ completed ⭐ ☆☆☆☆☆ 2026-10-21
TDS

Stop Ranking Agent Configs by Average Score

✅ completed ⭐ ☆☆☆☆☆ 2026-07-06
TDS

Single Agent vs Multi-Agent: When to Build a Multi-Agent System

✅ completed ⭐ ★★★★★★ 2026-05-04
TDS

You Probably Don’t Need an Agent Framework

✅ completed ⭐ ★★★★★★ 2026-06-17
VentureBeat

Ai Iq Is Here A New Site Scores Frontier Ai Models On The Human Iq Scale The Results Are Already Dividing Tech

✅ completed ⭐ ★★★★★★ 2026-06-23
VentureBeat

Microsoft’s open-source SkillOpt automatically upgrades AI agent skills without touching model weights

✅ completed ⭐ ★★★★★★ 2026-06-12
VentureBeat

DeepSWE blows up the AI coding leaderboard, crowns GPT-5.5, and finds Claude Opus exploiting a benchmark loophole

✅ completed ⭐ ★★★★★★ 2026-05-27
VentureBeat

Kimi K2.7-Code cuts thinking tokens 30% — but practitioners say the benchmarks don't check out

✅ completed ⭐ ★★★★★★ 2026-06-12