# 多流大型语言模型：关于提示、推理和I/O并行化/分离的新论文

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：atomicthumbs
- 发布时间：2026-05-22 15:32
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmpgmm2ks0gr2sljwfno36l6f
- 原文链接：https://arxiv.org/abs/2605.12460

## AI 摘要

一篇关于多流大型语言模型的新研究论文提出了将提示处理、推理计算以及输入输出过程进行分离与并行化的架构设计。该方法旨在提升大型语言模型在处理复杂任务时的效率与可扩展性，为构建更灵活、高效的AI系统提供了新的技术思路。

## 正文

Computer Science > Machine Learning

Title:Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

Abstract:The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since early instruction-tuned models like ChatGPT. Even advanced AI agents function on message exchange formats, successively exchanging messages with users, systems, with itself (i.e. chain-of-thought) and tools in a single stream of computation. This bottleneck to a single stream in chat models leads to a number of limitations: the agent cannot act (generate output) while reading, and in reverse, cannot react to new information while writing. Similarly, the agent cannot act while thinking and cannot think while reading or acting on information. In this work, we show that models can be unblocked by switching from instruction-tuning for sequential message formats to instruction-tuning for multiple, parallel streams of computation, splitting each role into a separate stream. Every forward pass of the language model then simultaneously reads from multiple input streams and generates tokens in multiple output streams, all of which causally depend on earlier timesteps. We argue that this data-driven change remedies a number of usability limitations as outlined above, improves model efficiency through parallelization, improves model security through better separation of concerns and can further improve model monitorability.

Comments: Preprint, 37 pages. Code at this https URL Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL) Cite as: arXiv:2605.12460 [cs.LG] (or arXiv:2605.12460v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2605.12460 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

View PDF

HTML (experimental)

TeX Source

Current browse context:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

Author

Venue

Institution

Topic

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.