Papers
arxiv:2510.03561

Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models

Published on Oct 3
· Submitted by Adam Filipek on Oct 7
Authors:

Abstract

The Reactive Transformer (RxT) addresses the limitations of stateless Transformers in conversational AI by using an event-driven paradigm with a fixed-size Short-Term Memory (STM) system, achieving linear scaling and low latency.

AI-generated summary

The Transformer architecture has become the de facto standard for Large Language Models (LLMs), demonstrating remarkable capabilities in language understanding and generation. However, its application in conversational AI is fundamentally constrained by its stateless nature and the quadratic computational complexity (O(L^2)) with respect to sequence length L. Current models emulate memory by reprocessing an ever-expanding conversation history with each turn, leading to prohibitive costs and latency in long dialogues. This paper introduces the Reactive Transformer (RxT), a novel architecture designed to overcome these limitations by shifting from a data-driven to an event-driven paradigm. RxT processes each conversational turn as a discrete event in real-time, maintaining context in an integrated, fixed-size Short-Term Memory (STM) system. The architecture features a distinct operational cycle where a generator-decoder produces a response based on the current query and the previous memory state, after which a memory-encoder and a dedicated Memory Attention network asynchronously update the STM with a representation of the complete interaction. This design fundamentally alters the scaling dynamics, reducing the total user-facing cost of a conversation from quadratic (O(N^2 cdot T)) to linear (O(N cdot T)) with respect to the number of interactions N. By decoupling response generation from memory updates, RxT achieves low latency, enabling truly real-time, stateful, and economically viable long-form conversations. We validated our architecture with a series of proof-of-concept experiments on synthetic data, demonstrating superior performance and constant-time inference latency compared to a baseline stateless model of comparable size.

Community

Paper author Paper submitter

Paper is introducing Reactive Transfomer (RxT) architecture for stateful real-time processing, that's outperforming same size stateless decoder-only model in small-scale experiments. Architecture advantages:

  • natively trained for conversations
  • linear conversation cost scaling instead of quadratic in LLMs
  • no prompt phase latency, thanks to asynchronous memory update
  • constant computational cost and memory usage for every message
  • natively encoded context in memory layers
  • better multi-turn conversations quality

Sign up or log in to comment

Models citing this paper 4

Datasets citing this paper 3

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.03561 in a Space README.md to link it from this page.

Collections including this paper 9