Related papers: From SWE-ZERO to SWE-HERO: Execution-free to Execu…

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve…

Text-to-SQL has emerged as a prominent research area, particularly with the rapid advancement of large language models (LLMs). By enabling users to query databases through natural language rather than SQL, this technology significantly…

Large language model (LLM) agents have shown great potential in solving real-world software engineering (SWE) problems. The most advanced open-source SWE agent can resolve over 27% of real GitHub issues in SWE-Bench Lite. However, these…

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.…

In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of…

Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this gap through a systematic study of data…

Supervisory controllers control cyber-physical systems to ensure their correct and safe operation. Synthesis-based engineering (SBE) is an approach to largely automate their design and implementation. SBE combines model-based engineering…

Small language models (1-3B) are practical to run locally, but individually limited on harder code generation tasks. We ask whether composing them into pipelines can recover some of that lost capability. We study code generation pipelines…

Computer-Aided Design (CAD) models are defined by their construction history: a parametric recipe that encodes design intent. However, existing large-scale 3D datasets predominantly consist of boundary representations (B-Reps) or meshes,…

An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks a systematic understanding of coding…

The rise of AI-assisted software engineering (SE 2.0), powered by Foundation Models (FMs) and FM-powered coding assistants, has shown promise in improving developer productivity. However, it has also exposed inherent limitations, such as…

Recent advances in statistical machine translation via the adoption of neural sequence-to-sequence models empower the end-to-end system to achieve state-of-the-art in many WMT benchmarks. The performance of such machine translation (MT)…

Quantization techniques are pivotal in reducing the memory and computational demands of deep neural network inference. Existing solutions, such as ZeroQuant, offer dynamic quantization for models like BERT and GPT but overlook crucial…

Benchmarks for large language models (LLMs) have predominantly assessed short-horizon, localized reasoning. Existing long-horizon suites (e.g. SWE-bench) rely on manually curated issues, so expanding or tuning difficulty demands expensive…

Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation…

Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed pipeline. We port the code-as-action paradigm of CodeAct (Wang et al., 2024a) to APE…

Automated environment configuration is a critical bottleneck in scaling software engineering (SWE) automation. To provide a reliable evaluation standard for this task, we present Multi-Docker-Eval benchmark. It includes 40 real-world…

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While…

We propose a novel model for learned query optimization which provides query hints leading to better execution plans. The model addresses the three key challenges in learned hint-based query optimization: reliable hint recommendation…

A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically.…