5 papers
Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts
Christoph Treude, Sebastian Baltes
Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrules. These files describe code e…
Improving LLM-Based Go Code Review through Issue-List Generation and Context Augmentation
Kexin Sun, Yucong Guan, Jiaqi Sun +6
LLMs have shown strong potential for automating code review, yet their practical utility depends heavily on the design of generation and context strategies. In this paper, we inves…
Deterministic vs. Probabilistic Summarisation: An Empirical Trade-off Study in Design Pattern Centric Java Code
Najam Nazar, Christoph Treude
Background: Automated code summarisation supports program comprehension and documentation, yet the relative strengths and limitations of deterministic (heuristic-based) and probabi…
Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
Hong Yi Lin, Chunhua Liu, Haoyu Gao +2
In today's AI-assisted software engineering landscape, developers increasingly depend on LLMs that are highly capable, yet inherently imperfect. The tendency of these models to pro…
Towards the First Code Contribution: Processes and Information Needs
Christoph Treude, Marco A. Gerosa, Igor Steinmacher
Newcomers to a software project must overcome many barriers before they can successfully place their first code contribution, and they often struggle to find information that is re…