用历史优质方案指导AI决策，提升安全场景下的协作正确性
Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration
- 基于历史高质量方案提取决策逻辑模式
- 通过形式化验证引导模型学习正确行为模式
- 适用于需高可靠性的智能系统设计与优化
尽管人工智能在安全关键领域取得显著进展，但决策输出的正确性验证及基于验证结果的设计仍面临挑战。本文提出正确性学习（Correctness Learning, CL），融合演绎验证方法与历史高质量方案的洞察，以增强人机协作。历史高质量方案中隐藏的典型模式，如共享资源下任务优先级的动态调整，为智能体的学习与决策提供关键指导。我们提出模式驱动的正确性学习（PDCL），通过演绎验证方法，形式化建模并推理系统智能体的自适应行为——即‘正确性模式’，捕捉这些方案中嵌入的逻辑关系。利用该逻辑信息作为指导，建立正确性判断与反馈机制，引导智能决策模型向历史高质量方案所体现的‘正确性模式’靠拢。在多种工况和核心参数下的大量实验验证了框架各组件的有效性，证明其在提升决策质量与资源优化方面的显著效果。
原文摘要 · Abstract (English)
Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design. We propose correctness learning (CL) to enhance human-AI collaboration integrating deductive verification methods and insights from historical high-quality schemes. The typical pattern hidden in historical high-quality schemes, such as change of task priorities in shared resources, provides critical guidance for intelligent agents in learning and decision-making. By utilizing deductive verification methods, we proposed patten-driven correctness learning (PDCL), formally modeling and reasoning the adaptive behaviors-or 'correctness pattern'-of system agents based on historical high-quality schemes, capturing the logical relationships embedded within these schemes. Using this logical information as guidance, we establish a correctness judgment and feedback mechanism to steer the intelligent decision model toward the 'correctness pattern' reflected in historical high-quality schemes. Extensive experiments across multiple working conditions and core parameters validate the framework's components and demonstrate its effectiveness in improving decision-making and resource optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。