{"ID":2856403,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11498","arxiv_id":"2510.11498","title":"ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding","abstract":"While Large Language Models (LLMs) excel at algorithmic code generation, they struggle with front-end development, where correctness is judged on rendered pixels and interaction. We present ReLook, an agentic, vision-grounded reinforcement learning framework that empowers an agent to close a robust generate--diagnose--refine loop by invoking a multimodal LLM (MLLM) as a tool. During training, the agent uses the MLLM-in-the-loop both as a visual critic--scoring code with screenshots--and as a source of actionable, vision-grounded feedback; a strict zero-reward rule for invalid renders anchors renderability and prevents reward hacking. To prevent behavioral collapse, we introduce Forced Optimization, a strict acceptance rule that admits only improving revisions, yielding monotonically better trajectories. At inference, we decouple the critic and run a lightweight, critic-free self-edit cycle, keeping latency comparable to base decoding while retaining most of the gains. Across three widely used benchmarks, ReLook consistently outperforms strong baselines in vision-grounded front-end code generation, highlighting the benefits of agentic perception, visual rewards, and training-inference decoupling.","short_abstract":"While Large Language Models (LLMs) excel at algorithmic code generation, they struggle with front-end development, where correctness is judged on rendered pixels and interaction. We present ReLook, an agentic, vision-grounded reinforcement learning framework that empowers an agent to close a robust generate--diagnose--...","url_abs":"https://arxiv.org/abs/2510.11498","url_pdf":"https://arxiv.org/pdf/2510.11498v1","authors":"[\"Yuhang Li\",\"Chenchen Zhang\",\"Ruilin Lv\",\"Ao Liu\",\"Ken Deng\",\"Yuanxing Zhang\",\"Jiaheng Liu\",\"Wiggin Zhou\",\"Bo Zhou\"]","published":"2025-10-13T15:05:50Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}