AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation

Jie Wu, Haoran Ma, Shisong Tang, Yulin Xu, Xiaoyu Kang, Jiechao Gao

ICML 2026 · Multi-agent systems and games › LLM agents · approach: GUI agent memory and trajectories

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 MulFCoder, a framework-conditioned multi-agent MLLM approach for generating runnable multi-framework (React/Vue/Angular) front-end code from UI screenshots.

Problem

Generating runnable front-end code from UI screenshots has mostly targeted HTML/CSS; multi-framework generation for React, Vue, and Angular is underexplored, and naive prompt changes leave large performance gaps and framework-specific error modes.

Approach

A framework-conditioned multi-agent design for MLLM-based screenshot-to-code generation that addresses framework-specific errors, rather than relying on prompt modification alone. Details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MulFCoder framework-conditioned multi-agent pipelineGPT-4o · Design2Code AngularCSR: 0.81 -> 0.90Improved
add MulFCoderQwen2.5-VL-7B · DesignBench AngularCSR: 0.62 -> 0.75Improved
add MulFCoderQwen2.5-VL-7B · Design2Code VueCSR: 0.83 -> 0.91Improved
add MulFCoderGPT-4o · DesignBench AngularCLIP score: 0.76 -> 0.76No clear effect
add MulFCoderGPT-4o · DesignBench ReactCSR: 0.94 -> 0.98Improved
add MulFCoder on weaker backbones versus stronger onesLLaVA-v1.5-7B vs Gemini-2.5-Pro · Design2Code AngularCSR gain: 0.65 -> 0.78 (LLaVA) vs 0.85 -> 0.91 (Gemini)Improved
add MulFCoder on Vanilla HTMLGPT-4o · Design2Code VanillaCLIP score: 0.91 -> 0.93Improved
apply MulFCoder bounded PATCH repair to Angular failuresMulFCoder · DesignBench Angularerror fix ratio: 31.2% average vs 50.4% ReactHurt
raise task difficulty from Easy to HardMulFCoder · DesignBench AngularCSR: 0.95 -> 0.62 (Gemini), 0.81 -> 0.10 (LLaVA)Hurt

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