About Me

Hi, I’m Myeongsoo Kim, an Applied Scientist at AWS AI Labs working on Kiro, an agentic AI development environment. I build coding agents and — just as importantly — the evaluation loops and trajectory analysis that show how well they actually work and where they fall short. A growing focus of mine is the loop between how agents perform in practice and how they get better: using benchmarks and trajectory analysis to find where they fall short, reproduce those cases, and feed what we learn back into improving the agent.

I earned my PhD in Computer Science from Georgia Tech, advised by Prof. Alessandro Orso.

Recent News

• [EMNLP 2026 - Under Review] “Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code”
  Myeongsoo Kim, Dingmin Wang, Siwei Cui, Farima Farmahinifarahani, Terry Yue Zhuo, Shweta Garg, Baishakhi Ray, Rajdeep Mukherjee, Varun Kumar
  [arXiv]

• [ACL 2026] “CodeStruct: Code Agents over Structured Action Spaces”
  Myeongsoo Kim, Joe Hsu, Dingmin Wang, Shweta Garg, Varun Kumar, Murali Krishna Ramanathan
  [arXiv]

• [ICSE 2025 Industry - 🏆 Distinguished Paper Award] “Aster: Natural and Multi-Language Unit Test Generation with LLMs”
  Rangeet Pan, Myeongsoo Kim, Rahul Krishna, Raju Pavuluri, Saurabh Sinha
  [IEEE CS] [arXiv]

• [NeurIPS 2025 D&B] “CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance”
  Myeongsoo Kim, Shweta Garg, Baishakhi Ray, Varun Kumar, Anoop Deoras
  [arXiv]

• [FSE 2025] “LlamaRestTest: Effective REST API Testing with Small Language Models”
  Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
  [ACM DL]

• [ICSE 2025 Research] “A Multi-Agent Approach for REST API Testing with Semantic Graphs and LLM-Driven Inputs”
  Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
  [IEEE]

• [ICSE 2025 Demo] “AutoRestTest: A Tool for Automated REST API Testing Using LLMs and MARL”
  Tyler Stennett, Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
  [IEEE]

Research Interests

My work centers on:

• Coding agents for real software engineering tasks
• Evaluation loops and benchmarks for measuring agent performance
• Trajectory analysis and failure diagnosis for coding agents
• Large Language Models (LLMs) for code generation and understanding

Publications

You can find my research publications on my Google Scholar profile.

Get in Touch

Feel free to reach out via email or connect with me on LinkedIn and GitHub.