AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Circuit-Think: A Multimodal Reasoning Framework for Automated Circuit-to-Netlist Translation with Trajectory-Guided Reinforcement Learning

Yuqi Jiang, Yupeng Hu, Jinyuan Deng, Xiaotian Qiu, Yucheng Cui, Xuyang He, Ruidong Li, Qi Sun, Cheng Zhuo

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Circuit-Think, a multimodal reasoning framework for translating circuit images into netlists, trained with trajectory-guided reinforcement learning.

Problem

VLMs struggle with circuit images because of diverse component symbols and complex connections, which hinders understanding physical layouts and reasoning about electrical connectivity for circuit-to-netlist translation.

Approach

A multimodal reasoning framework for circuit-to-netlist translation that combines trajectory-guided reinforcement learning to teach VLMs to reason about physical layout and electrical connections.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with TGRL instead of GRPOQwen2.5-VL-7B · Circuit image-netlist test setSPICE netlist accuracy: 40.23 -> 60.17Improved
train with TGRL instead of SFTQwen2.5-VL-7B · Circuit image-netlist test setSPICE netlist accuracy: 34.78 -> 60.17Improved
add strict step-wise format constraint (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 39.21 -> 73.27Improved
tighten format constraint from soft to strict (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 52.69 -> 73.27Improved
add device recognition reward after port reward (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 45.93 -> 48.13Improved
add connection reasoning reward (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 48.13 -> 73.27Improved
add port/device type classification (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 47.13 -> 73.27Improved
add port/device bbox localization (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 49.91 -> 73.27Improved
add step-by-step port-device-connection trajectory (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 35.38 -> 73.27Improved
add logic consistency reward Rlogic (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 63.25 -> 73.27Improved
add reflective learning (ablation)Circuit-Think · Circuit image-netlist test setSPICE netlist accuracy: 65.76 -> 73.27Improved
add reflective learning (ablation)Circuit-Think · Circuit image-netlist test setlogic consistency: 70.10 -> 85.76Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy