AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic

Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging. This process requires accurate visual-to-symbolic construction of circuit structure from images and correct multi-step symbolic derivation, both of which impose strict correctness requirements. This work proposes AutoVSR, an automated framework for visual-to-symbolic generation of circuit expressions using Vision Language Models (VLMs). By reconstructing circuit diagrams into an executable intermediate representation (Executable IR) and leveraging a symbolic solver for reasoning, AutoVSR significantly improves the accuracy of symbolic expression generation. AutoVSR introduces two key innovations: an IR construction method guided by component rule retrieval and verification-based feedback, and a symbolic solver implemented as a planning agent equipped with a symbolic tool library for reliable multi-step derivation. Compared with end-to-end VLM approaches and specialized methods on the main symbolic expression generation task, AutoVSR achieves accuracy improvements of 30.01--59.45% and 41.96--51.84%, respectively. Moreover, AutoVSR surpasses closed-source state-of-the-art VLMs in inference cost and computational efficiency. Code is available at https://github.com/LongfeiLi1/AutoVSR.

Engineers use mathematical formulas to understand and predict how an electronic circuit will behave, such as how a signal changes as it passes through the circuit. However, deriving these formulas directly from a circuit diagram is difficult, because a system must first read the diagram correctly and then perform several exact reasoning steps without small mistakes. We built AutoVSR, an AI framework that turns a circuit schematic image into a machine-checkable description of the circuit, and then uses symbolic reasoning tools to derive the final formula. Instead of asking a vision-language model to guess the answer directly, AutoVSR checks whether its intermediate circuit description is valid and repairs it when errors are found. It also separates high-level reasoning from exact calculation, allowing the AI to plan the solution while specialized tools carry out the mathematical derivation. This makes circuit formula generation more accurate, reliable, and efficient than direct vision-language model approaches. AutoVSR can help automate circuit analysis and make AI systems more useful for engineering design.