paper-with-me

Papers

Code Aesthetics with Agentic Reward Feedback

2025-10-27 · Bang Xiao, Lingjie Jiang, Shaohan Huang, Tengchao Lv, Yupan Huang, Xun Wu, Lei Cui, Furu Wei arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.23272

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningCode Generation

Similar Papers 제목 키워드 기반

Agentic Design Review System

2025-08-14 · Sayan Nag, K J Joseph, Koustava Goswami, Vlad I Morariu 외 arxiv

Evaluating graphic designs involves assessing it from multiple facets like alignment, composition, aesthetics and color choices. Evaluating designs in a holistic way involves aggregating feedback from individual expert r…

Graph Matching

AesRM: Improving Video Aesthetics with Expert-Level Feedback

2026-04-30 · Yujin Han, Yujie Wei, Yefei He, Xinyu Liu 외 arxiv

Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors and cinematic lighting, beyond visual fidelity. Prior work on visual…

Video Generation

Exploring Reasoning Reward Model for Agents

2026-01-29 · Kaixuan Fan, Kaituo Feng, Manyuan Zhang, Tianshuo Peng 외 arxiv

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such …

Reinforcement Learning

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

2026-08-31 · Xingyuan Bu, Chengru Song, Hao Zhou, Tao Zhou 외 hf

Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realisti…

Video Generation

RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System

2026-02-02 · Yinjie Wang, Tianbao Xie, Ke Shen, Mengdi Wang 외 arxiv

We propose RLAnything, a reinforcement learning framework that dynamically forges environment, policy, and reward models through closed-loop optimization, amplifying learning signals and strengthening the overall RL syst…

Reinforcement Learning