arXiv:2607. 18356v1 Announce Type: cross Abstract: Maintaining up-to-date code documentation is difficult in fast-moving repositories because design knowledge is scattered across source files and pull requests.
arXiv:2607. 09224v1 Announce Type: cross Abstract: Version control systems are essential for collaborative software development, yet tools like git remain challenging for many practitioners.
SlackBench is a new benchmark that evaluates AI agents on realistic collaborative research and engineering workflows, requiring joint reasoning over workplace communication and evolving repository state. The benchmark is built from privacy‑preserving reenactments of real academic projects, providing reproducible environments with multi‑party dialogue, code changes from GitHub, and Google Docs. It contains 140 queries covering heterogeneous‑source search, abstention, summarization, and inference over long conversations, and shows that current models perform well below the ceiling, indicating significant room for improvement.
The paper introduces RAG4Tickets, an AI system that uses Retrieval-Augmented Generation to improve ticket resolution on JIRA and GitHub. It embeds historical tickets, comments, and pull request data with Sentence-Transformers, indexes them with FAISS, and then uses a Large Language Model to generate grounded, explainable resolution suggestions based on retrieved evidence. Experiments show higher precision, recall, faster resolution times, and better developer acceptance compared to existing methods.
The paper reports on building a research-software catalog using a coding agent, starting from a three‑day hackathon prototype and moving to public deployment. It details the engineering work needed—adversarial review, data‑quality checks, browser validation, and publication safeguards—to ensure reliable operation, noting that silent failures were more problematic than crashes. The authors then examine applying these lessons to a larger, human‑curated portal (MateriApps) that combines curated metadata, external documentation, vector search, and local language‑model generation, finding that explicit validation, monitoring, and repeated review remain essential for AI‑assisted software portals.
arXiv:2608.29834v1 Announce Type: new Abstract: Collaborative conversations frequently contain references whose targets are indirect rather than named: resolving "this looks like the fix discussed ye...
arXiv:2608.29204v1 Announce Type: cross Abstract: Generative AI-based software engineering agents are becoming routine contributors to real-world software projects. On GitHub, developers can assign t...
arXiv:2607. 06482v1 Announce Type: cross Abstract: Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings.
arXiv:2606. 07538v1 Announce Type: cross Abstract: Large language model (LLM)-based agents provide a novel paradigm for the automated processing of remote sensing(RS) data.
ComBeautify is a tool that automatically generates Conventional Commits Specification (CCS)-compliant commit messages by combining context-preserving summarization of Git diffs with large language models. It learns commit categories from historical data rather than relying on manually curated definitions, and also produces the CCS description component. Evaluation on 13 languages, 6,500 repositories, and over 20 million commits shows that project-specific training can outperform generic baselines by up to three times, with summarization accuracy reaching 95.25% on a manually curated dataset.
arXiv:2609.20886v1 Announce Type: cross Abstract: Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tab...
The paper explores whether natural‑language documentation aids coding agents in fixing software bugs and introduces a roundtrip benchmark that evaluates code descriptions by regenerating code and testing it. It finds that description completeness, not length, determines fidelity, and presents an optimizer that can produce fully faithful descriptions that generalize to new files. However, experiments across two model families and ten repositories show that such compact documentation does not improve an agent’s ability to resolve real repository issues compared to using the issue alone.