发表机构
North-West University, RSA; University of Pretoria, RSA; Mankind Research Labs, Sandton（南非北开普大学; 南非彼得里亚大学; 沙顿人类研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大语言模型输出难检测错误的问题，提出海维赛德连续性的滚动系数框架，将推理重新表述为谓词门控状态转换，结合模型置信度与并行验证信号，防止无效状态传播，降低认知熵。
AI 中文摘要
大语言模型生成的流畅输出可能有误，且难以检测。我们引入海维赛德连续性的滚动系数（HCRC），这是一个先验证的执行框架，将推理重新表述为由海维赛德门控的谓词门控状态转换。HCRC结合模型置信度与来自并行工作架构的独立验证信号，仅在满足预定义正确性谓词时才允许执行推进。
英文摘要
Large language models (LLMs) generate fluent outputs that can be wrong. Unlike humans, who often exhibit cues when providing false information, LLMs produce errors that are difficult to detect because autoregressive decoding provides no mechanism for verifying intermediate reasoning before state progression. We introduce Heaviside Continuity of Rolling Coefficients (HCRC), a verification-first execution framework that reformulates inference as predicate-gated state transitions governed by a Heaviside Gate. HCRC combines model confidence with independent verification signals from a parallel worker architecture, allowing execution to advance only when predefined correctness predicates are satisfied. This prevents invalid intermediate states from propagating, reducing epistemic entropy without modifying the underlying model. We evaluate HCRC on software-engineering and reasoning tasks across thirteen proposers from four providers. On capable proposers, the gate reduces the false-completion rate (FCR) from 4--7% to 0% while remaining latency-competitive and, in some settings, faster than the unwrapped model. On weaker proposers, it converts false completions into honest halts instead of corrupting downstream state. Beyond benchmarking, HCRC has operated for months as the production control plane of an agentic coding environment, authorizing file mutations, verification-driven progress reporting, and memory compaction. These results establish HCRC as a general framework for verification-driven LLM execution, showing that reliable reasoning can be achieved through principled execution control rather than model scale alone.
CommentsThe article needs revision please
