一作ACL 2026Poster· Natural Language Processing
R e L ook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
Yuhang Li · Chenchen Zhang · Ruilin Lv · Ao Liu · Ken Deng · Yuanxing Zhang · JIAHENG LIU · Bo Zhou
摘要
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 robu...