Our paper Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications was accepted to ASE 2026! The work investigates how LLM-based agent applications are tested in practice and identifies opportunities for improving automated test generation in the future.
News
-
Tangent accepted to ASE 2026!
-
Joining the ACM Future Leaders of AI cohort
I was selected for the inaugural Future Leaders of AI cohort at the ACM AI Leadership Summit. I’m really grateful for the opportunity and excited to meet the other members and exchange ideas at the summit!
-
Sakura accepted to ISSTA 2026!
Our paper Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions was accepted to ISSTA 2026! Looking forward to seeing everyone in Oakland, California this October.
-
AutoRestTest wins the SBFT REST League 🎉
AutoRestTest took first place in all three categories of the SBFT REST League tool competition: fault detection, overall efficiency, and overall effectiveness. Big thanks to the organizers for putting together a great competition, and congrats to all the participating teams! The tool is open source, if you’d like to take a look.