Related papers: SWE-Hub: A Unified Production System for Scalable,…
Open-source scientific software is a major driver of scientific progress, yet its development and reuse remain difficult in collaborative settings. Researchers repeatedly face four recurring challenges: discovering and reproducing existing…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines,…
Large Language Models (LLMs) have achieved impressive results on static code-generation benchmarks, but real-world software development unfolds as a continuous stream of evolving issues, fixes, and feature requests. We introduce…
Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a…
Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especially when model parameters are less than 100B. While smaller…
Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…
Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped…
Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely…
We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…
The software engineering research community is productive, yet it faces a constellation of challenges: swamped review processes, metric-driven incentives, distorted publication practices, and increasing pressures from AI, scale, and…
Existing browser agent benchmarks face a fundamental trilemma: real-website benchmarks lack reproducibility due to content drift, controlled environments sacrifice realism by omitting real-web noise, and both require costly manual curation…
The vision of End-User Software Engineering (EUSE) is to empower non-professional users with full control over the software development lifecycle. It aims to enable users to drive generative software development using only natural language…
As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via…
LLM-based agent systems are emerging as a new software paradigm and have been widely adopted across diverse domains such as medicine, robotics, and programming. However, maintaining these systems requires substantial effort, as they are…
Resolving issues on code repositories is an important part of software engineering. Various recent systems automatically resolve issues using large language models and agents, often with impressive performance. Unfortunately, most of these…
Developing modern systems software is a complex task that combines business logic programming and Software Performance Engineering (SPE). The later is an experimental and labor-intensive activity focused on optimizing the system for a given…
As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and…
With the rapid advances of powerful multimodal models such as GPT-4o, Nano Banana, and Seedream 4.0 in Image Editing, the performance gap between closed-source and open-source models is widening, primarily due to the scarcity of…
Instruction-based image editing has emerged as a key capability for unified multimodal models (UMMs), yet constructing large-scale, diverse, and high-quality editing datasets without costly proprietary APIs remains challenging. Previous…