QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling
Long-horizon reasoning is vulnerable to early errors that compromise later decisions. We present QART, the Quantum-Augmented Reasoning Transformer, a quantum--classical hybrid architecture combining a backbone language model with quantum encoding, CIM-based QUBO optimization, and quantum decoding. Semantic information can come from hidden representations or model-generated text; detailed encoding and optimization procedures remain proprietary. Under explicit assumptions, we establish a conditional asymptotic reliability separation from single-trajectory autoregressive LLMs. For a common task family with aligned optimality and acceptance criteria, autoregressive acceptance probability tends to zero when cumulative conditional risk of irreversible errors diverges. QART's task-optimal-path recovery probability remains bounded away from zero if conditional probabilities for optimal-path coverage and semantic fidelity, spectral certification, dynamical reachability, and faithful readout remain uniformly positive under a specified resource schedule. The architecture alone does not imply these bounds. Paired measurements on six long-horizon benchmarks using DeepSeek V4 Flash, GLM-5.3, and GPT-5.5 xhigh in a Codex agent environment favor QART in 14 of 15 backbone--benchmark pairs. Relative gains reach 84.0% on SciCode, 47.6% on $τ^3$-Bench, and 44.4% on Terminal-Bench 4.0; the DeepSeek V4 Flash configuration regresses by 7.8% on DeepSWE. These results do not directly validate the asymptotic separation. Potential quantum scaling laws are formulated as conditional hypotheses. A quantum-advantage interpretation requires a demonstrated CIM quantum advantage over strong classical solvers and its transfer to end-to-end reasoning after all system overheads.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Quantum-classical hybrid models based on error correction for time series forecasting
Time series forecasting largely benefits from combining the strengths of different models, especially using a scheme where a model corrects another model by capturing supplementary patterns from forecasting errors. Concu…
Time Series ForecastingToward Practical Quantum Machine Learning: A Novel Hybrid Quantum LSTM for Fraud Detection
We present a novel hybrid quantum-classical neural network architecture for fraud detection that integrates a classical Long Short-Term Memory (LSTM) network with a variational quantum circuit. By leveraging quantum phen…
Fraud DetectionQuantum Machine LearningGeneralization Bounds in Hybrid Quantum-Classical Machine Learning Models
Hybrid classical-quantum models aim to harness the strengths of both quantum computing and classical machine learning, but their practical potential remains poorly understood. In this work, we develop a unified mathemati…
Generalization BoundsLearning TheoryThe Role of Quantum in Hybrid Quantum-Classical Neural Networks: A Realistic Assessment
Quantum machine learning has emerged as a promising application domain for near-term quantum hardware, particularly through hybrid quantum-classical models that leverage both classical and quantum processing. Although nu…
Quantum Machine LearningHybrid Quantum-Classical Stochastic Networks with Boltzmann Layers
Quantum Machine Learning (QML) has the potential to significantly advance the state-of-the-art in artificial intelligence, due to recent developments in quantum computing hardware and algorithm design. Particularly, an …
Quantum Machine Learning