Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Chrysalis-QEC: A Model-Free Single-Shot Quantum Decoder via Noise-Agnostic Meta-Reinforcement Learning

Yassin Gaffar

Published Aug 16, 2026• 0 citations
Publisher

Abstract

Quantum Error Correction (QEC) is indispensable for protecting fragile quantum states against environmental decoherence and hardware imperfections. Traditionally, the Minimum Weight Perfect Matching (MWPM) algorithm has served as the benchmark decoder; however, its heavy geometric calculations introduce significant processing latencies and require strict, pre-calibrated prior knowledge of physical error distributions. Deep learning decoders have emerged to address these constraints but commonly suffer from catastrophic forgetting when operational environments dynamically fluctuate. To resolve these challenges, this work introduces Chrysalis-QEC, a novel model-free Meta-Reinforcement Learning (Meta-RL) decoder optimized for real-time, low-latency, single-shot quantum error correction. Implemented via a customized Gymnasium environment integrated with the Stim simulation library, the architecture employs a sequential curriculum learning framework driven by Proximal Policy Optimization (PPO). By progressively transferring policy parameters across escalating noise baselines (from 5% to 7% and 10%), the agent maps the underlying topological structures of error syndromes rather than memorizing static error probabilities. Under dynamic shock testing featuring stochastic noise variations jumping between 1% and 10%, Chrysalis-QEC achieves decoding success rates of 94.00% for distance-3 and 95.00% for distance-5 configurations. The proposed framework demonstrates superior stability, significantly lower decoding variance, and instantaneous adaptation compared to the baseline MWPM decoder, validating its efficacy as a noise-agnostic solution for real-world fault-tolerant quantum computing architectures.

DOI
10.5281/zenodo.21967491

Related papers

ADAPTIVE REINFORCEMENT LEARNING FOR QUANTUM ERROR CORRECTION UNDER NON-STATIONARY NOISE: A CONTINUAL/META-RL FRAMEWORK FOR DRIFT-ROBUST DECODING

P. Suresh Varma, M. V. Rama Sundari

Quantum error correction (QEC) decoders are usually trained and evaluated assuming stationary physical noise.Real superconducting and trapped-ion processors, however, exhibit noise that drifts over calibration cycles, shifts abruptly because of twolevel-system defects and cosmic-ray events, and varies across qubits.Static decoders, whether algorithmic (minimum-weight perfect matching, union-find) or learned (such as AlphaQubit), degrade when deployed noise diverges from the training distribution, and full retraining is costly and can cause catastrophic forgetting.This paper proposes Adaptive-RL-QEC, a research framework that formulates decoding and noise adaptation as a reinforcement learning problem over a non-stationary Markov decision process with an unobserved noise-regime variable.It couples a lightweight online noise-regime estimator with a continual/meta-reinforcement-learning decoding policy that adapts within a bounded number of syndrome rounds without catastrophic P.

INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY•Oct 5, 2026•0 citations

Hardware-in-the-Loop Reinforcement Learning for Quantum Error Correction: A Systems-Engineering Approach to Latency-Aware Decoding

Hiroshi Tanaka, Kenji Yamamoto, Takeshi Saito

The scalability of fault-tolerant quantum computing is strictly bounded by the performance and latency of Quantum Error Correction (QEC) decoding systems. While Reinforcement Learning (RL) has emerged as a promising approach for deriving optimal decoding policies, current Deep Q-Network (DQN) agents are overwhelmingly trained using idealized software simulators. These simulators employ deterministic latency models that drastically fail to capture the stochastic load noise, memory contention, thermal throttling, and bus jitter inherent to real-world hardware deployment on Field-Programmable Gate Arrays (FPGAs). In this paper, we propose a comprehensive Hardware-in-the-Loop (HIL) Reinforcement Learning architecture that physically situates the FPGA in the RL environment feedback loop. By directly offloading syndrome processing jobs to the FPGA hardware during training, the DQN agent observes the exact microarchitectural execution latency as its environmental reward. We formulate a robust, systems-engineering oriented framework that captures true edge-deployment constraints. Our extensive HIL empirical results demonstrate that agents trained against true hardware telemetry develop distinct decoding strategies that actively avoid routing congestion in the FPGA fabric, yielding up to a $42\%$ reduction in long-tail latency events and improving the effective logical error rate under strict real-time decoding constraints.

•Jul 21, 2026•0 citations

SAGE-QEC: Structure-Aware Gated Error Correction for Surface-Code Memories Under Structured Noise

Asia Alhammadi, Mohammed Al-Absi

Abstract Quantum error-correction decoders must convert noisy syndrome records into logical decisions while operating under strict latency and reliability constraints. Minimum-weight perfect matching (MWPM) remains a strong baseline for surface-code decoding because it is fast, interpretable, and exact for its graphlike optimization problem [1–8]. However, the graphlike independent-error approximation can become mismatched when syndrome records contain temporal drift, measurement corruption, crosstalk, bursts, or mixtures of mechanisms [9–18]. We introduce SAGE-QEC, a failure-aware selective decoder that retains nominal PyMatching as its default decision and learns when an observable syndrome structure warrants an alternative candidate. SAGE-QEC uses train-frozen structure thresholds, a candidate ranker, validation-only policy selection, and a paired blind evaluation. Across 45 simulator conditions, SAGE-QEC reduced the aggregate logical error rate from 27.1285% for PyMatching to 24.8320%, corresponding to an 8.47% relative reduction. The campaign used rotated surface-code memory circuits at distances 3, 5, and 7, nominal circuit parameters 0.002, 0.003, and 0.005, five seeds, and four test regimes withheld from training: Burst-3, Temporal Drift, Crosstalk, and Mixed Noise. The test set contained 81,000 paired shots. All twelve distance-by-regime aggregate comparisons favored SAGE-QEC in the executed campaign, with paired bootstrap intervals below zero for SAGE-QEC minus PyMatching. The result is evidence of a reproducible simulator-level improvement, not a claim of universal decoder superiority. SAGE-QEC currently uses logical-output proxy candidates rather than a complete physical correction search, and its intervention rate remains high under distribution shift. It has not yet been compared with a fully calibrated correlated-noise space-time PyMatching baseline or hardware calibration data. We therefore characterize SAGE-QEC as a strong qualification-stage prototype and release a complete audit protocol for the next industrial validation stage.

•Sep 9, 2026•0 citations

Reinforcement Learning for Enhanced Advanced QEC Architecture Decoding

Yidong Zhou, Lingyi Kong, Yifeng Peng +1 more

The advent of promising quantum error correction (QEC) codes with efficient resource utilization and high-performance fault-tolerant quantum memories signifies a critical step towards realizing practical quantum computation. While surface codes have been a dominant approach, their limitations have spurred the development of more advanced QEC architectures. These advanced codes often present increased complexity, demanding innovative decoding methodologies. This work investigates the application of reinforcement learning (RL) techniques, including hybrid and multi-agent approaches, to enhance the decoding of various advanced QEC architectures. By leveraging the ability of RL to learn optimal strategies from noisy syndrome measurements, we explore the potential for achieving improved logical error rates and scalability compared to traditional decoding methods. Our approach examines the adaptation of reinforcement learning to exploit the structural properties of these modern QEC models. We also explore the benefits of combining different RL algorithms to address the multifaceted nature of the decoding problem, considering factors such as code degeneracy and real-world noise characteristics. With our proposed method, we are able to demonstrate that an autonomously trained agent can derive decoding schemes for the complex decoding requirement of advanced QEC architectures.

quant-pharXiv:2601.19279•Jan 28, 2026•0 citations

Hardware-in-the-Loop Reinforcement Learning for Quantum Error Correction: A Systems-Engineering Approach to Latency-Aware Decoding

Yamamoto Kenji, Tanaka Hiroshi, Takeshi Saito

The scalability of fault-tolerant quantum computing is strictly bounded by the performance and latency of Quantum Error Correction (QEC) decoding systems. While Reinforcement Learning (RL) has emerged as a promising approach for deriving optimal decoding policies, current Deep Q-Network (DQN) agents are overwhelmingly trained using idealized software simulators. These simulators employ deterministic latency models that drastically fail to capture the stochastic load noise, memory contention, thermal throttling, and bus jitter inherent to real-world hardware deployment on Field-Programmable Gate Arrays (FPGAs). In this paper, we propose a comprehensive Hardware-in-the-Loop (HIL) Reinforcement Learning architecture that physically situates the FPGA in the RL environment feedback loop. By directly offloading syndrome processing jobs to the FPGA hardware during training, the DQN agent observes the exact microarchitectural execution latency as its environmental reward. We formulate a robust, systems-engineering oriented framework that captures true edge-deployment constraints. Our extensive HIL empirical results demonstrate that agents trained against true hardware telemetry develop distinct decoding strategies that actively avoid routing congestion in the FPGA fabric, yielding up to a $42\%$ reduction in long-tail latency events and improving the effective logical error rate under strict real-time decoding constraints.

•Jul 21, 2026•0 citations

Adaptive Quantum Error Correction via Reinforcement Learning

Jincheng Zhang

Quantum error correction (QEC) is a crucial element in the realization of fault-tolerant quantum computation. However, traditional QEC schemes often rely on pre-determined, static parameters, which may not be optimally suited for the specific noise characteristics present in a given quantum hardware. This work introduces a novel approach to QEC that leverages reinforcement learning (RL) to dynamically adapt the error correction protocol in real-time. The system learns to optimize the parameters of the QEC code, such as measurement schedules and decoding strategies, based on continuous feedback from the quantum hardware. This adaptive approach promises to significantly improve the performance and efficiency of QEC, reducing the overhead associated with error correction and enhancing the fidelity of quantum computations. The core claim of this paper is that quantum error correction is computationally intensive and requires precise control over quantum systems. The central mechanism involves employing reinforcement learning to optimize the parameters of quantum error correction protocols in real-time, adapting to the specific noise characteristics of the quantum hardware. This represents a new automation of the QEC process.

•Sep 7, 2026•0 citations
Quantum Error Correction (QEC) is indispensable for protecting fragile quantum states against environmental decoherence and hardware imperfections. Traditionally, the Minimum Weight Perfect Matching (MWPM) algorithm has served as the benchmark decoder; however, its heavy geometric calculations introduce significant processing latencies and require strict, pre-calibrated prior knowledge of physical error distributions. Deep learning decoders have emerged to address these constraints but commonly suffer from catastrophic forgetting when operational environments dynamically fluctuate. To resolve these challenges, this work introduces Chrysalis-QEC, a novel model-free Meta-Reinforcement Learning (Meta-RL) decoder optimized for real-time, low-latency, single-shot quantum error correction. Implemented via a customized Gymnasium environment integrated with the Stim simulation library, the architecture employs a sequential curriculum learning framework driven by Proximal Policy Optimization (PPO). By progressively transferring policy parameters across escalating noise baselines (from 5% to 7% and 10%), the agent maps the underlying topological structures of error syndromes rather than memorizing static error probabilities. Under dynamic shock testing featuring stochastic noise variations jumping between 1% and 10%, Chrysalis-QEC achieves decoding success rates of 94.00% for distance-3 and 95.00% for distance-5 configurations. The proposed framework demonstrates superior stability, significantly lower decoding variance, and instantaneous adaptation compared to the baseline MWPM decoder, validating its efficacy as a noise-agnostic solution for real-world fault-tolerant quantum computing architectures.
Quantum error correction (QEC) decoders are usually trained and evaluated assuming stationary physical noise.Real superconducting and trapped-ion processors, however, exhibit noise that drifts over calibration cycles, shifts abruptly because of twolevel-system defects and cosmic-ray events, and varies across qubits.Static decoders, whether algorithmic (minimum-weight perfect matching, union-find) or learned (such as AlphaQubit), degrade when deployed noise diverges from the training distribution, and full retraining is costly and can cause catastrophic forgetting.This paper proposes Adaptive-RL-QEC, a research framework that formulates decoding and noise adaptation as a reinforcement learning problem over a non-stationary Markov decision process with an unobserved noise-regime variable.It couples a lightweight online noise-regime estimator with a continual/meta-reinforcement-learning decoding policy that adapts within a bounded number of syndrome rounds without catastrophic P.
The scalability of fault-tolerant quantum computing is strictly bounded by the performance and latency of Quantum Error Correction (QEC) decoding systems. While Reinforcement Learning (RL) has emerged as a promising approach for deriving optimal decoding policies, current Deep Q-Network (DQN) agents are overwhelmingly trained using idealized software simulators. These simulators employ deterministic latency models that drastically fail to capture the stochastic load noise, memory contention, thermal throttling, and bus jitter inherent to real-world hardware deployment on Field-Programmable Gate Arrays (FPGAs). In this paper, we propose a comprehensive Hardware-in-the-Loop (HIL) Reinforcement Learning architecture that physically situates the FPGA in the RL environment feedback loop. By directly offloading syndrome processing jobs to the FPGA hardware during training, the DQN agent observes the exact microarchitectural execution latency as its environmental reward. We formulate a robust, systems-engineering oriented framework that captures true edge-deployment constraints. Our extensive HIL empirical results demonstrate that agents trained against true hardware telemetry develop distinct decoding strategies that actively avoid routing congestion in the FPGA fabric, yielding up to a 42%42\%42% reduction in long-tail latency events and improving the effective logical error rate under strict real-time decoding constraints.
Abstract Quantum error-correction decoders must convert noisy syndrome records into logical decisions while operating under strict latency and reliability constraints. Minimum-weight perfect matching (MWPM) remains a strong baseline for surface-code decoding because it is fast, interpretable, and exact for its graphlike optimization problem [1–8]. However, the graphlike independent-error approximation can become mismatched when syndrome records contain temporal drift, measurement corruption, crosstalk, bursts, or mixtures of mechanisms [9–18]. We introduce SAGE-QEC, a failure-aware selective decoder that retains nominal PyMatching as its default decision and learns when an observable syndrome structure warrants an alternative candidate. SAGE-QEC uses train-frozen structure thresholds, a candidate ranker, validation-only policy selection, and a paired blind evaluation. Across 45 simulator conditions, SAGE-QEC reduced the aggregate logical error rate from 27.1285% for PyMatching to 24.8320%, corresponding to an 8.47% relative reduction. The campaign used rotated surface-code memory circuits at distances 3, 5, and 7, nominal circuit parameters 0.002, 0.003, and 0.005, five seeds, and four test regimes withheld from training: Burst-3, Temporal Drift, Crosstalk, and Mixed Noise. The test set contained 81,000 paired shots. All twelve distance-by-regime aggregate comparisons favored SAGE-QEC in the executed campaign, with paired bootstrap intervals below zero for SAGE-QEC minus PyMatching. The result is evidence of a reproducible simulator-level improvement, not a claim of universal decoder superiority. SAGE-QEC currently uses logical-output proxy candidates rather than a complete physical correction search, and its intervention rate remains high under distribution shift. It has not yet been compared with a fully calibrated correlated-noise space-time PyMatching baseline or hardware calibration data. We therefore characterize SAGE-QEC as a strong qualification-stage prototype and release a complete audit protocol for the next industrial validation stage.
The advent of promising quantum error correction (QEC) codes with efficient resource utilization and high-performance fault-tolerant quantum memories signifies a critical step towards realizing practical quantum computation. While surface codes have been a dominant approach, their limitations have spurred the development of more advanced QEC architectures. These advanced codes often present increased complexity, demanding innovative decoding methodologies. This work investigates the application of reinforcement learning (RL) techniques, including hybrid and multi-agent approaches, to enhance the decoding of various advanced QEC architectures. By leveraging the ability of RL to learn optimal strategies from noisy syndrome measurements, we explore the potential for achieving improved logical error rates and scalability compared to traditional decoding methods. Our approach examines the adaptation of reinforcement learning to exploit the structural properties of these modern QEC models. We also explore the benefits of combining different RL algorithms to address the multifaceted nature of the decoding problem, considering factors such as code degeneracy and real-world noise characteristics. With our proposed method, we are able to demonstrate that an autonomously trained agent can derive decoding schemes for the complex decoding requirement of advanced QEC architectures.
The scalability of fault-tolerant quantum computing is strictly bounded by the performance and latency of Quantum Error Correction (QEC) decoding systems. While Reinforcement Learning (RL) has emerged as a promising approach for deriving optimal decoding policies, current Deep Q-Network (DQN) agents are overwhelmingly trained using idealized software simulators. These simulators employ deterministic latency models that drastically fail to capture the stochastic load noise, memory contention, thermal throttling, and bus jitter inherent to real-world hardware deployment on Field-Programmable Gate Arrays (FPGAs). In this paper, we propose a comprehensive Hardware-in-the-Loop (HIL) Reinforcement Learning architecture that physically situates the FPGA in the RL environment feedback loop. By directly offloading syndrome processing jobs to the FPGA hardware during training, the DQN agent observes the exact microarchitectural execution latency as its environmental reward. We formulate a robust, systems-engineering oriented framework that captures true edge-deployment constraints. Our extensive HIL empirical results demonstrate that agents trained against true hardware telemetry develop distinct decoding strategies that actively avoid routing congestion in the FPGA fabric, yielding up to a 42%42\%42% reduction in long-tail latency events and improving the effective logical error rate under strict real-time decoding constraints.
Quantum error correction (QEC) is a crucial element in the realization of fault-tolerant quantum computation. However, traditional QEC schemes often rely on pre-determined, static parameters, which may not be optimally suited for the specific noise characteristics present in a given quantum hardware. This work introduces a novel approach to QEC that leverages reinforcement learning (RL) to dynamically adapt the error correction protocol in real-time. The system learns to optimize the parameters of the QEC code, such as measurement schedules and decoding strategies, based on continuous feedback from the quantum hardware. This adaptive approach promises to significantly improve the performance and efficiency of QEC, reducing the overhead associated with error correction and enhancing the fidelity of quantum computations. The core claim of this paper is that quantum error correction is computationally intensive and requires precise control over quantum systems. The central mechanism involves employing reinforcement learning to optimize the parameters of quantum error correction protocols in real-time, adapting to the specific noise characteristics of the quantum hardware. This represents a new automation of the QEC process.