Multi-Stream LLMs: new paper on parallelizing/separating prompts, thinking, I/O

A new paper proposes "Multi-Stream LLMs," which replace the traditional single-stream, sequential message format of AI agents with multiple parallel streams of computation. This architecture allows the model to simultaneously read, think, and generate output, addressing limitations where agents cannot act while reading or think while acting. The authors argue this data-driven change improves efficiency, security, and monitorability by better separating these roles.

Computer Science Machine Learning Submitted on 12 May 2026 Title:Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs View PDF HTML experimental 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. References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? Connected Papers What is Connected Papers? Litmaps What is Litmaps? scite Smart Citations What are Smart Citations? Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? CatalyzeX Code Finder for Papers What is CatalyzeX? DagsHub What is DagsHub? Gotit.pub What is GotitPub? Hugging Face What is Huggingface? ScienceCast What is ScienceCast? Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? CORE Recommender What is CORE? IArxiv Recommender What is IArxiv? 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.