Related papers: SWE-QA-Pro: A Representative Benchmark and Scalabl…
We present Code-QA-Bench, a fully automated framework for synthesizing repository-level code understanding benchmarks that separates genuine code comprehension from documentation recall and pretraining memorization. The framework makes two…
Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution…
Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains…
Automating real-world software engineering tasks remains challenging for large language model (LLM)-based agents due to the need for long-horizon reasoning over large, evolving codebases and making consistent decisions across interdependent…
Automated issue solving seeks to autonomously identify and repair defective code snippets across an entire codebase. SWE-Bench has emerged as the most widely adopted benchmark for evaluating progress in this area. While LLM-based agentic…
Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…
Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limited by the complexity of environment setup, unit test…
Advancing complex reasoning in large language models relies on high-quality, verifiable datasets, yet human annotation remains cost-prohibitive and difficult to scale. Current synthesis paradigms often face a recurring trade-off:…
Rapidly increasing context lengths have led to the assumption that large language models (LLMs) can directly reason over entire codebases. Concurrently, recent advances in LLMs have enabled strong performance on software engineering…
Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their…
Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase.…
Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…
Despite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub…
We introduce QiboAgent, a reference implementation designed to serve as a practitioner's guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development…
Large language model agents have made strong progress on software engineering, yet current systems suffer from a context coupling problem: the standard code editing interface conflates code inspection, modification planning, and edit…
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models…
Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavor: developers interpret high-level…
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…
Large language models (LLMs) are transforming automated program repair (APR) through agent-based approaches that localize bugs, generate patches, and verify fixes. However, the lack of high-quality, scalable training datasets, especially…
Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the standard approach of repeatedly sampling trajectories from scratch is…