💻 Technology 1d ago

Kimi K2.6 runs agents for days — and exposes the limits of enterprise orchestration

VentureBeat
VentureBeat tech
View Channel →
Kimi K2.6 runs agents for days — and exposes the limits of enterprise orchestration
Source ↗ 👁 0 💬 0
Most orchestration frameworks were built for agents that run for seconds or minutes. Now that agents are running for hours — and in some cases days — those frameworks are starting to crack.Several model providers, such as Anthropic with Claude Code and OpenAI with Codex, introduced early support for long-horizon agents through multi-session tasks, subagents and background execution. However, these systems sometimes assume agents are still operating within bounded-time workflows even when they ru

Comments (0)

Sign in to join the discussion

More Like This

📰
Apple Releases iOS 26.4.2 and iPadOS 26.4.2
Thurrott.com · 1h ago
Google Confirms Gemini-Powered Siri Coming Later This Year
MacRumors: Mac News and Rumors - All Stories · 1h ago
📰
Don't wait to buy a MacBook Neo for school - here's why
Latest news · 1h ago
📰
OpenAI announces workspace agents in ChatGPT, letting teams create Codex-powered shared agents for complex tasks, and says they are "an evolution of GPTs" (OpenAI)
Techmeme · 1h ago
Apple TV’s acclaimed London crime thriller is back with new season
9to5Mac · 1h ago
OpenAI updates ChatGPT with Codex-powered ‘workspace agents’ for teams
9to5Mac · 1h ago