Call For Papers: Special Issue on Software Engineering for and with Trustworthy Large Language Models

This special issue focuses on software engineering foundations, methods, tools, benchmarks, and empirical studies for developing, evaluating, and responsibly integrating trustworthy large language models in software engineering. The scope follows two complementary directions: software engineering for trustworthy LLM-based systems, including RAG pipelines, tool-using agents, multi-agent systems, and multi-modal LLM services; and software engineering with trustworthy LLM integration across the development lifecycle, including coding, testing, review, maintenance, deployment, and governance.

Topics of interest include, but are not limited to:

• Reliability, robustness, and safety of LLM-based software engineering tools and workflows
• Evaluation and benchmarking of code LLMs, coding agents, and LLM-based SE systems
• Trustworthy agentic, RAG-based, and multi-modal software systems
• Testing, verification, validation, and runtime monitoring of LLM-based systems
• Security, privacy, prompt injection, jailbreaks, red-teaming, and misuse risks
• Grounding, hallucination mitigation, provenance, and evidence-based guarantees
• Fairness, bias, transparency, explainability, and accountability of LLMs for SE
• Human-AI collaboration in software development
• LLMOps, CI/CD policy gates, compliance, governance, and risk management
• Technical debt, maintainability, and long-term impacts of AI-generated code
• Empirical studies of LLM adoption in software engineering practice
• Open benchmarks, datasets, tools, and artifacts for trustworthy LLM-based SE

The special issue will invite extended versions of selected papers from LLMTrust 2026 workshop at FSE, while also being open to broader submissions aligned with the scope.

Submission

Deadline: December 31, 2026

Submission link: via Springer, TBA

Guest editor list:

• Sumon Biswas (sumon@case.edu)
• Shibbir Ahmed
• Sayem Mohammad Imtiaz
• Hridesh Rajan