# Quantum adaptive agents with efficient long-term memories

arXiv: https://arxiv.org/abs/2108.10876 · HTML: https://mlsanity.com/paper/2108.10876/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 74 references that are in the map.
- First posted on arXiv 24 Aug 2021.

## Builds on (most cited first, 5 of 5)

- [Quantum-enhanced machine learning](https://mlsanity.com/paper/1610.08251/) (2016)
- [Machine learning & artificial intelligence in the quantum domain](https://mlsanity.com/paper/1709.02779/) (2017)
- [Learning Causal State Representations of Partially Observable Environments](https://mlsanity.com/paper/1906.10437/) (2019)
- [Memory compression and thermal efficiency of quantum implementations of non-deterministic hidden Markov models](https://mlsanity.com/paper/2105.06285/) (2021)
- [Leveraging Environmental Correlations: The Thermodynamics of Requisite Variety](https://mlsanity.com/paper/1609.05353/) (2016)

## Built on by (most cited first, 6 of 6)

- [Neural networks leverage nominally quantum and post-quantum representations](https://mlsanity.com/paper/2507.07432/) (2025)
- [Time-Warping Invariant Quantum Recurrent Neural Networks via Quantum-Classical Adaptive Gating](https://mlsanity.com/paper/2301.08173/) (2023)
- [Quantum-Classical Hybrid Information Processing via a Single Quantum System](https://mlsanity.com/paper/2209.00497/) (2022)
- [Identifiability and minimality bounds of quantum and post-quantum models of classical stochastic processes](https://mlsanity.com/paper/2509.03004/) (2025)
- [Hybrid Classical-Quantum architecture for vectorised image classification of hand-written sketches](https://mlsanity.com/paper/2407.06416/) (2024)
- [An Irreducible Quantum Advantage in Aligning World Models with Reality](https://mlsanity.com/paper/2608.19779/) (2026)

## Abstract (arXiv)

Central to the success of adaptive systems is their ability to interpret signals from their environment and respond accordingly -- they act as agents interacting with their surroundings. Such agents typically perform better when able to execute increasingly complex strategies. This comes with a cost: the more information the agent must recall from its past experiences, the more memory it will need. Here we investigate the power of agents capable of quantum information processing. We uncover the most general form a quantum agent need adopt to maximise memory compression advantages, and provide a systematic means of encoding their memory states. We show these encodings can exhibit extremely favourable scaling advantages relative to memory-minimal classical agents, particularly when information must be retained about events increasingly far into the past.