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

2026-07-13

AI Summary

This work addresses the challenging task of automatically generating high-precision symbolic expressions from circuit diagram images, which requires jointly solving visual structural recognition and multi-step symbolic reasoning. The authors propose AutoVSR, a novel framework that synergistically integrates a vision-language model with a symbolic solver: the former reconstructs the circuit diagram into an executable intermediate representation, while the latter performs reliable multi-step derivations through rule retrieval, verification feedback mechanisms, and a planning-based reasoning agent. Experimental results demonstrate that AutoVSR substantially outperforms both end-to-end vision-language models and existing specialized methods, achieving accuracy gains of 30.01–59.45% and 41.96–51.84%, respectively, on the primary task, while also exhibiting superior inference efficiency compared to state-of-the-art closed-source vision-language models.

Abstract

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.

Problem

• Symbolic Expression Generation
• Circuit Schematic
• Visual-to-Symbolic Reasoning
• Vision Language Models
• Circuit Analysis

Innovation

• Visual-to-Symbolic Reasoning
• Executable Intermediate Representation
• Symbolic Solver
• Vision Language Models
• Circuit Schematic Understanding