Tootfinder

I get the desire for live coding interviews, you can't just take people's word that they know how to do it.
But what's the point in throwing Advent of Code style problems at me and interrupting a naive or incorrect approach before I even start implementing it? Let me write unoptimized code for you and then make it better! I'm not going to write the perfect implementation first try for every problem, but I can show you my process and prove I can write _some_ code.
…

D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
Muqi Zou (Jing), Hongyu Cai (Jing), Hongwei Wu (Jing), Zion Leonahenahe Basque (Jing), Arslan Khan (Jing), Berkay Celik (Jing), Dave (Jing), Tian (Fish), Antonio Bianchi (Fish), Ruoyu (Fish), Wang, Dongyan Xu
https://arxiv.org/abs/2506.10125…

D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
Decompilers, which reconstruct human-readable source code from binary executables, are vital to many security tasks. Yet, despite recent advances, their output often suffers from syntactic and semantic errors and remains difficult to read. Recently, with the advent of large language models (LLMs), researchers began to explore the potential of LLMs to refine decompiler output. Nevertheless, our study of these approaches reveals significant limitations, such as introducing new errors and relying …

UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
Boxi Yu, Yuxuan Zhu, Pinjia He, Daniel Kang
https://arxiv.org/abs/2506.09289 https://

UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world problems based on GitHub issues and their corresponding pull requests. However, the manually written test cases included in these pull requests are often insufficient, allowing generated patches to pass the tests without resolving the underlying issue. To addre…

MLLM-Based UI2Code Automation Guided by UI Layout Information
Fan Wu, Cuiyun Gao, Shuqing Li, Xin-Cheng Wen, Qing Liao
https://arxiv.org/abs/2506.10376 htt…

MLLM-Based UI2Code Automation Guided by UI Layout Information
Converting user interfaces into code (UI2Code) is a crucial step in website development, which is time-consuming and labor-intensive. The automation of UI2Code is essential to streamline this task, beneficial for improving the development efficiency. There exist deep learning-based methods for the task; however, they heavily rely on a large amount of labeled training data and struggle with generalizing to real-world, unseen web page designs. The advent of Multimodal Large Language Models (MLLMs…

Understanding Software Engineering Agents Through the Lens of Traceability: An Empirical Study
Ira Ceka, Saurabh Pujar, Shyam Ramji, Luca Buratti, Gail Kaiser, Baishakhi Ray
https://arxiv.org/abs/2506.08311

Understanding Software Engineering Agents Through the Lens of Traceability: An Empirical Study
With the advent of large language models (LLMs), software engineering agents (SWE agents) have emerged as a powerful paradigm for automating a range of software tasks -- from code generation and repair to test case synthesis. These agents operate autonomously by interpreting user input and responding to environmental feedback. While various agent architectures have demonstrated strong empirical performance, the internal decision-making worfklows that drive their behavior remain poorly understoo…

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
Melika Sepidband, Hamed Taherkhani, Song Wang, Hadi Hemmati
https://arxiv.org/abs/2505.23953

Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
Automatic code generation has gained significant momentum with the advent of Large Language Models (LLMs) such as GPT-4. Although many studies focus on improving the effectiveness of LLMs for code generation, very limited work tries to understand the generated code's characteristics and leverage that to improve failed cases. In this paper, as the most straightforward characteristic of code, we investigate the relationship between code complexity and the success of LLM generated code. Using a la…

This https://arxiv.org/abs/2409.14644 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

An Effective Approach to Embedding Source Code by Combining Large Language and Sentence Embedding Models
The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code clustering. However, existing methods for source code embedding, including those based on LLMs, often rely on costly supervised training or fine-tuning for domain adaptation. This paper proposes a novel approach to embedding source code by combining large la…

This https://arxiv.org/abs/2411.03079 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation
Static Application Security Testing (SAST) tools are critical to software quality, identifying potential code issues early in development. However, they often produce false positive warnings that require manual review, slowing down development. Thus, automating false positive mitigation (FPM) is essential. The advent of Large Language Models (LLMs), with their strong abilities in natural language and code understanding, offers promising avenues for FPM. Yet current LLM-based FPM method faces tw…