# FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback

arXiv: https://arxiv.org/abs/2601.04203 · HTML: https://mlsanity.com/paper/2601.04203/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset](https://mlsanity.com/paper/2403.09029/) (2024)
- [WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch](https://mlsanity.com/paper/2505.03733/) (2025)
- [Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping](https://mlsanity.com/paper/2411.03292/) (2024)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping](https://mlsanity.com/paper/2410.16232/) (2024)
- [FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow](https://mlsanity.com/paper/2505.17399/) (2025)
- [FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation](https://mlsanity.com/paper/2506.13832/) (2025)
- [WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code](https://mlsanity.com/paper/2506.07818/) (2025)
- [WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning](https://mlsanity.com/paper/2509.22644/) (2025)
- [ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments](https://mlsanity.com/paper/2502.19852/) (2025)

## Built on by (most cited first, 14 of 14)

- [SWE-Together: Evaluating Coding Agents in Interactive User Sessions](https://mlsanity.com/paper/2606.29957/) (2026)
- [MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants](https://mlsanity.com/paper/2603.09652/) (2026)
- [The Verification Horizon: No Silver Bullet for Coding Agent Rewards](https://mlsanity.com/paper/2606.26300/) (2026)
- [WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models](https://mlsanity.com/paper/2604.18224/) (2026)
- [LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks](https://mlsanity.com/paper/2603.22744/) (2026)
- [StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns](https://mlsanity.com/paper/2606.19613/) (2026)
- [LiveEvalBench: Toward Open-World Evaluation for Web Generation](https://mlsanity.com/paper/2608.03689/) (2026)
- [EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants](https://mlsanity.com/paper/2608.29387/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Omni2Web: Benchmarking Audiovisual Website Development](https://mlsanity.com/paper/2609.23417/) (2026)
- [Framework and Benchmark for Code-Driven Agentic Testing in Web Development](https://mlsanity.com/paper/2609.00081/) (2026)
- [MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding](https://mlsanity.com/paper/2609.14992/) (2026)
- [WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective](https://mlsanity.com/paper/2609.15387/) (2026)
- [WatchPoint: Executable User Feedback for Real-World Agentic Web Development](https://mlsanity.com/paper/2609.26204/) (2026)

## Abstract (arXiv)

We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generation with multi-modal feedback. In front-end development, visual artifacts such as sketches, mockups and annotated creenshots are essential for conveying design intent, yet their role in multi-turn code generation remains largely unexplored. To address this gap, we focus on the front-end development task and curate FronTalk, a collection of 100 multi-turn dialogues derived from real-world websites across diverse domains such as news, finance, and art. Each turn features both a textual instruction and an equivalent visual instruction, each representing the same user intent. To comprehensively evaluate model performance, we propose a novel agent-based evaluation framework leveraging a web agent to simulate users and explore the website, and thus measuring both functional correctness and user experience. Evaluation of 20 models reveals two key challenges that are under-explored systematically in the literature: (1) a significant forgetting issue where models overwrite previously implemented features, resulting in task failures, and (2) a persistent challenge in interpreting visual feedback, especially for open-source vision-language models (VLMs). We propose a strong baseline to tackle the forgetting issue with AceCoder, a method that critiques the implementation of every past instruction using an autonomous web agent. This approach significantly reduces forgetting to nearly zero and improves the performance by up to 9.3% (56.0% to 65.3%). Overall, we aim to provide a solid foundation for future research in front-end development and the general interaction dynamics of multi-turn, multi-modal code generation. Code and data are released at https://github.com/shirley-wu/frontalk