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

arXiv: https://arxiv.org/abs/2510.03561 · HTML: https://mlsanity.com/paper/2510.03561/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Memformer: A Memory-Augmented Transformer for Sequence Modeling](https://mlsanity.com/paper/2010.06891/) (2020)
- [Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling](https://mlsanity.com/paper/2209.07634/) (2022)
- [Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance](https://mlsanity.com/paper/2504.07989/) (2025)
- [Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction](https://mlsanity.com/paper/2510.01817/) (2025)

## Built on by (most cited first, 1 of 1)

- [TensorBLEU: Vectorized GPU-based BLEU Score Implementation for Per-Sentence In-Training Evaluation](https://mlsanity.com/paper/2510.05485/) (2025)

## Abstract (arXiv)

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(L2)) 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(N2 · T)) to linear (O(N · 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.