About ReSAISE
Artificial Intelligence is now deeply embedded in software engineering workflows, from code generation and program repair to vulnerability detection, test generation, maintenance, and developer support. Large Language Models and agentic AI systems make these workflows more powerful, but they also introduce dependability questions that software engineering research cannot treat as an afterthought.
ReSAISE'26 brings together researchers and practitioners from the AI and Software Engineering communities to discuss how AI-based solutions for software engineering can be made reliable, secure, trustworthy, and useful in real development settings. The workshop continues the ReSAISE focus on reliability and security while reflecting the growing role of LLMs, AI coding assistants, and multi-agent software engineering systems.
We welcome contributions that study the development, deployment, evaluation, and operation of reliable and secure AI for software engineering, including methods, empirical studies, tools, benchmarks, experience reports, and lessons learned from negative or unexpected results.
Call for Papers Registration Info
Topics of Interest
This call for papers invites researchers and practitioners to explore reliability, security, and quality aspects of AI in Software Engineering. Topics include, but are not limited to:
AI Security and Privacy
- Adversarial attacks and defenses
- Privacy-preserving AI techniques
- Security threats and countermeasures
- Secure model training and deployment
- Authentication, access control, compliance, and regulatory requirements
- Security challenges in LLM-based and multi-agent software engineering systems
AI System Integrity and Quality
- Data quality, bias mitigation, and dataset curation
- Evaluation approaches, benchmarks, and reproducibility
- Robustness, resilience, fault tolerance, and incident response
- System monitoring, maintenance, and lifecycle management
- Emergent behaviors in agentic and multi-agent AI systems
AI Implementation and Operation for Software Engineering
- AI-enabled threat detection, defect detection, and vulnerability analysis
- Secure code generation and program synthesis
- Automated testing, test generation, and test assessment
- Code analysis, refinement, maintenance, and program repair
- Reliable integration of AI tools into software development workflows
LLMs, Agents, and Human-AI Collaboration
- AI coding assistants and agentic software engineering
- Multi-agent LLM frameworks for collaborative software development
- Coordination, communication, and failure modes in AI agent systems
- Explainable AI for software engineering tasks and developer decision support
- Developer trust, attribution, accountability, and human-in-the-loop workflows
Experiences, Sustainability, and Case Studies
- Practical experiences and real-world case studies
- Open issues and lessons learned from negative results
- Green AI and sustainable AI-enabled software development
- Industrial adoption, governance, and responsible AI practices