# Code Aesthetics with Agentic Reward Feedback

arXiv: https://arxiv.org/abs/2510.23272 · HTML: https://mlsanity.com/paper/2510.23272/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset](https://mlsanity.com/paper/2403.09029/) (2024)
- [Rule Based Rewards for Language Model Safety](https://mlsanity.com/paper/2411.01111/) (2024)
- [PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback](https://mlsanity.com/paper/2307.14936/) (2023)
- [AI-Generated Content (AIGC): A Survey](https://mlsanity.com/paper/2304.06632/) (2023)
- [Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems](https://mlsanity.com/paper/2502.19328/) (2025)
- [Image Aesthetic Assessment: An Experimental Survey](https://mlsanity.com/paper/1610.00838/) (2016)
- [Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code](https://mlsanity.com/paper/2412.02764/) (2024)
- [HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment](https://mlsanity.com/paper/2503.23907/) (2025)
- [VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation](https://mlsanity.com/paper/2506.03930/) (2025)

## Built on by (most cited first, 6 of 6)

- [Vision-Guided Iterative Refinement for Frontend Code Generation](https://mlsanity.com/paper/2604.05839/) (2026)
- [Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation](https://mlsanity.com/paper/2605.30000/) (2026)
- [DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents](https://mlsanity.com/paper/2605.17439/) (2026)
- [1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World](https://mlsanity.com/paper/2602.18548/) (2026)
- [From Subjective Judgments to Auditable Standards:Protocol-Guided AI Auditing of Website Redundancy](https://mlsanity.com/paper/2608.21476/) (2026)
- [Editable Visual Design](https://mlsanity.com/paper/2609.04034/) (2026)

## Abstract (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.