pith. sign in

arxiv: 2503.07096 · v1 · pith:AXR7QRXFnew · submitted 2025-03-10 · 💻 cs.AI

Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration

classification 💻 cs.AI
keywords correctnessschemeslearninghigh-qualityhistoricaldecision-makingdeductivepattern
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.