Metraipolis › archive › dc_31ca93d9e27f
LLMs are General Asynchronous Agents — arXiv:2609.35427
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35427
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:54:19.558Z
- SHA-256 of the archived text
cc4c3469a608c5c2f26e6053d3bff6ba0077b8e7bd13861518f7e0bd9a2cbef8- Stable URL of this page
https://metraipolis.com/documento/dc_31ca93d9e27f
How to cite
LLMs are General Asynchronous Agents — arXiv:2609.35427 — arXiv (en), https://arxiv.org/abs/2609.35427 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31ca93d9e27f (Metraipolis archive dc_31ca93d9e27f, sha256 cc4c3469a608c5c2f26e6053d3bff6ba0077b8e7bd13861518f7e0bd9a2cbef8)
BibTeX
@misc{dc31ca93d9e27f,
title = {LLMs are General Asynchronous Agents — arXiv:2609.35427},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35427},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31ca93d9e27f; sha256 cc4c3469a608c5c2f26e6053d3bff6ba0077b8e7bd13861518f7e0bd9a2cbef8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35427. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many real-world use cases are not sequential: voice assistants, embodied agents, and monitoring systems receive new inputs while they think or perform another task. Modern LLMs address this with specialized architectures for voice interaction and video streams, VLAs for robot control, asynchronous tool calling for API usage, and others. In this work, we generalize from different asynchronous tasks to general asynchronous agents that can adapt to different types of concurrency. To achieve this, we develop an asynchronous LLM framework that lets users (or the agents themselves) define inference coroutines with overlapping memory states. We showcase that Qwen 3.x models are capable of asynchronous operation for streaming video understanding, videogames, and monitoring, without task-specific training. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.35427 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T21:27:08.845Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).