{"ID":2849601,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23272","arxiv_id":"2510.23272","title":"Code Aesthetics with Agentic Reward Feedback","abstract":"Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug fixing, they struggle with visually-oriented coding tasks, often producing suboptimal aesthetics. In this paper, we introduce a new pipeline to enhance the aesthetic quality of LLM-generated code. We first construct AesCode-358K, a large-scale instruction-tuning dataset focused on code aesthetics. Next, we propose agentic reward feedback, a multi-agent system that evaluates executability, static aesthetics, and interactive aesthetics. Building on this, we develop GRPO-AR, which integrates these signals into the GRPO algorithm for joint optimization of functionality and code aesthetics. Finally, we develop OpenDesign, a benchmark for assessing code aesthetics. Experimental results show that combining supervised fine-tuning on AesCode-358K with reinforcement learning using agentic reward feedback significantly improves performance on OpenDesign and also enhances results on existing benchmarks such as PandasPlotBench. Notably, our AesCoder-4B surpasses GPT-4o and GPT-4.1, and achieves performance comparable to large open-source models with 480B-685B parameters, underscoring the effectiveness of our approach.","short_abstract":"Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug fixing, they struggle with visually-oriented coding tasks, often producing suboptimal aesthetics. In this paper, we introduce a new pipelin...","url_abs":"https://arxiv.org/abs/2510.23272","url_pdf":"https://arxiv.org/pdf/2510.23272v1","authors":"[\"Bang Xiao\",\"Lingjie Jiang\",\"Shaohan Huang\",\"Tengchao Lv\",\"Yupan Huang\",\"Xun Wu\",\"Lei Cui\",\"Furu Wei\"]","published":"2025-10-27T12:32:33Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}