QART：一种面向长时程推理的量子-经典混合架构——探索通向量子扩展的条件路径
QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling
- QuantumMind（量子心智）
- Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
- The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
- Shenzhen Institute of Data Economy（深圳数据经济研究院）
- Nanyang Technological University（南洋理工大学）
- The Hong Kong Polytechnic University（香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出量子-经典混合架构QART，结合量子编码、CIM优化与量子解码，在长时程推理基准上多数超越自回归模型，并给出条件渐近可靠性分离与量子扩展假设。
AI中文摘要：
长时程推理容易受到早期错误的影响，这些错误会危及后续决策。我们提出QART（量子增强推理Transformer），这是一种量子-经典混合架构，将骨干语言模型与量子编码、基于CIM的QUBO优化以及量子解码相结合。语义信息可以来自隐藏表示或模型生成的文本；详细的编码和优化流程仍属专有。在明确假设下，我们建立了与单轨迹自回归大语言模型相比的条件渐近可靠性分离。对于具有对齐最优性和接受标准的常见任务族，当不可逆错误的累积条件风险发散时，自回归接受概率趋于零。如果最优路径覆盖和语义保真度、谱认证、动力学可达性以及忠实读出的条件概率在指定资源调度下保持一致为正，则QART的任务最优路径恢复概率仍保持有界远离零。架构本身并不隐含这些界限。在Codex智能体环境中，使用DeepSeek V4 Flash、GLM-5.3和GPT-5.5 xhigh对六个长时程基准进行配对测量，在15个骨干-基准配对中，QART在14个上占优。相对增益在SciCode上达到84.0%，在$\ au^3$-Bench上达到47.6%，在Terminal-Bench 4.0上达到44.4%；DeepSeek V4 Flash配置在DeepSWE上退步了7.8%。这些结果并不直接验证渐近分离。潜在的量子扩展定律被表述为条件假设。量子优势的解释需要证明CIM相对于强经典求解器的量子优势，并在所有系统开销之后将其转移到端到端推理中。
英文摘要：
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.
