Meta researchers show Qwen 3.x can run as general asynchronous agents without task-specific training
yresearch · hf · 2026-09-30
A new paper, "LLMs are General Asynchronous Agents," argues that modern LLM agents are stuck in sequential read-think-act loops while real use cases like voice assistants, embodied agents, and monitoring need to ingest new input mid-thought. The authors build a general asynchronous LLM framework where users (or agents themselves) define inference coroutines with overlapping memory states, unifying specialized architectures (voice, video streaming, async tool calls) under one paradigm. They show Qwen 3.x models handle streaming video understanding, videogames, and monitoring asynchronously — with no task-specific training.
More from AGI Musings
- From "we can't control AGI" to "embrace the merger": one researcher tracks the shifting Overton window — danfaggella · 2026-09-30
- a16z essay tackles the 'labs will kill every AI startup' panic: app layer isn't dead — hugs · 2026-09-30
- OpenAI's dots, Meta's Muse and Grok Bot: the cloud-agent war replaces OpenClaw — FuSheng_0306 · 2026-09-30
- Anil Seth's biological naturalism essay against AI consciousness draws mass commentary collection — anilkseth · 2026-09-30
- As AI makes intelligence cheap, judgment becomes the scarce advantage — r0ck3t23 · 2026-09-30
- Build in Public Era Is Over: Agents Erase the Tech Head Start, Devs Say — pramodk73 · 2026-09-30