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
- Critic pushes back: Anthropic leaking ideology into model weights is a red flag — gerardsans · 2026-11-16
- Alpha School accused of "counseling out" low-gain students as founders push back on selection bias claims — benjaminjriley · 2026-11-16
- Netflix lands Joseph Gordon-Levitt's AI thriller with Rachel McAdams, sparking debate on AI apocalypse blockbusters — ShakeelHashim · 2026-11-16
- Caine Prize confirms 2026 winner amid AI-use allegations — ShakeelHashim · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16
- A diagram for judging quality in cultural artefacts: coded meaning and exemplary moves — round · 2026-11-16