Christoph Treude
4 papers · Latest:
Software Engineering
Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files
Developers are operationalizing AI ethics by encoding behavioral rules into repository context files for AI agents.
2605.05584
Software EngineeringAccountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap
This paper analyzes AI coding assistant Terms of Service, revealing how responsibility is shifted to users, and proposes a research roadmap for accountable agents.
2605.04532
Software EngineeringWhen AI Models Become Dependencies: Studying the Evolution of Pre-Trained Model Reuse in Downstream Software Systems
A study finds pre-trained models (PTMs) evolve distinctly from traditional software libraries when used as dependencies, accumulating rather than being replaced.
2604.17940
Software EngineeringFine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
This paper introduces fine-grained confidence calibration methods for LLMs in automated code revision tasks, improving reliability and trustworthiness.
2604.06723
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.