arXiv AI
RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 12
VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
arXiv:2605. 26144v2 Announce Type: replace-cross Abstract: We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents.
arXiv AI
Aug 25
ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation
ATP‑Bench proposes a new benchmark for evaluating agentic tool planning in multimodal large language models (MLLMs) that generate interleaved text-and-image responses. The benchmark contains 7,702 QA pairs, including 1,592 visual‑question‑answer pairs, across eight categories and 25 visual‑critical intents, all verified by humans. A Multi‑Agent MLLM‑as‑a‑Judge (MAM) system is introduced to assess tool‑call precision, missed opportunities, and overall response quality without relying on ground‑truth references.
arXiv AI
Jul 14
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
arXiv:2607. 10079v1 Announce Type: new Abstract: Digital Adoption Platforms (DAPs) are embedded overlays widely used on web systems to guide users through operations inside a page, helping them get started with unfamiliar interfaces quickly.
arXiv Computer Vision
Sep 3
Rendering-in-the-Loop: An Execution-Driven Agent for Interactive Web Development
RILA is an execution‑driven agent that integrates browser rendering into the generation loop for interactive web development. It uses an Action Interaction Verification module to replay reference interactions on generated pages, collecting execution‑aware observations, and an Execution‑aware Rendering Score to jointly assess interaction correctness and visual fidelity during iterative optimization. A data synthesis pipeline further augments training data, enabling RILA to significantly improve interaction and visual quality across foundation models, even outperforming larger one‑shot generators.
arXiv AI
Jun 2
Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
arXiv:2606. 00154v1 Announce Type: cross Abstract: Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-end development.
arXiv Machine Learning
Jun 11
FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
arXiv:2601. 04203v2 Announce Type: replace-cross Abstract: 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.