CodeMates 2026
Next-Gen Code Development with Collaborative AI Agents

08:50 - 09:00 Opening Remarks by Behrooz Omidvar-Tehrani (AWS)

09:00 - 10:00 Invited Talk: From IntelliCode to GitHub Copilot: Human-Centered Coding Agents at Scale, in person talk by Shengyu Fu (Micrososft CoreAI)

10:00 - 10:15 Paper Presentation: From Vibe to Verifiable Spec-Driven Development: A Demo of Intent and Realization Engineering, presented in-person by Dayi Lin (Centre for Software Excellence, Huawei Canada)

10:15 - 10:30 Paper Presentation: Multi-Agent Framework for Automated Cloud Security Assessment presented virtually by Omer Tripp (Amazon)

10:30 - 11:00 Coffee Break ☕️

11:00 - 11:45 Invited Talk: Claude Code: One Year Later, virtual talk by Dalton Flanagan (Anthropic)

11:45 - 12:00 Paper Presentation: Improving Grammar Constraints Generation Alignment by Sampling Highly Probable Playouts, presented in-person by Killian Susini (Université Paris Dauphine)

12:00 - 12:15 Paper Presentation: Agentic Reinforcement Learning for Real-World Code Repair, presented virtually by Alborz Geramifard (LinkedIn)

12:15 - 14:00 Lunch

14:00 - 15:00 Invited Talk: Agentic AI for Software: Lessons in Trust, in person talk by Abhik Roychoudhury (National University of Singapore)

15:00 - 15:45 Invited Talk: Code Assistants: from Code Completion to Coding Agents, virtual talk by Baptiste Rozière (Mistral)

15:45 - 16:30 Panel: Shengyu Fu (in-person), Abhik Roychoudhury (in-person), Omer Tripp (in-person), Dalton Flanagan (remote), Alborz Geramifard (remote), Baptiste Rozière (remote)

16:30 - 16:45 Paper Presentation: CAT: Coverage-aware Testing — Structured Test Suite Generation for Coding Agent Handoff

16:45 - 17:00 Paper Presentation: LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost, presented in-person by Shila Chew (MasterCard)

17:00 - 17:05 Closing Remarks by Shweta Garg and Behrooz Omidvar-Tehrani (AWS)

Workshop Topic and Focus

We explore how AI agents collaborate in modern software engineering. We study single agent systems that work with humans, multi agent systems that coordinate among themselves, and hybrid approaches. We focus on interaction models, handoffs, workflow design, and on safeguards that preserve human agency while leveraging AI capability. We also ask how to make these systems reliable, auditable, and safe for production, and what verification and evaluation frameworks are needed.

Topics of Interest

• Collaborative AI architectures for software development

• Multi-agent coordination strategies

• Human–AI workflow integration and handoff mechanisms

• Preserving human expertise and agency in AI-assisted coding

• Interaction design in IDEs, CLIs, and collaborative environments

• Trust, reliability, and safety in collaborative coding agents

• Verification, validation, and auditing frameworks

• Evaluation methodologies and benchmarks for collaboration

• User studies and empirical developer experience evaluations

• Industrial deployments and case studies of AI coding agents

• Applications in planning, implementation, debugging, and testing

• Lessons from systems such as GitHub Copilot, Amazon Kiro, IBM Bob, Cursor AI, and Asimov