Uploaded May 2026 | Updated November 2026, 11 hours ago
What if AI agents could check their work as they go? This verification method extracts verifiable properties from natural language and evaluates them using symbolic or model-based verifiers. Interwhen, a new open-source library, enables real-time verification of each step, helping agents act more safely and reliably in complex, real-world tasks.
Paper: arxiv.org/abs/2602.11202
GitHub: github.com/microsoft/interwhen
This session aired on May 14, 2026, at Microsoft Research Forum, Season 2 Episode 4.
Register for the series to hear about new releases: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=msr_researchforum_YTDescription
Explore all previous episodes: https://aka.ms/researchforumYTplaylist
What if AI agents could check their work as they go? This verification method extracts verifiable properties from natural language and evaluates them using symbolic or model-based verifiers. Interwhen, a new open-source library, enables real-time verification of each step, helping agents act more safely and reliably in complex, real-world tasks.
Paper: arxiv.org/abs/2602.11202
GitHub: github.com/microsoft/interwhen
This session aired on May 14, 2026, at Microsoft Research Forum, Season 2 Episode 4.
Register for the series to hear about new releases: microsoft.com/en-us/research/event/microsoft-research-forum/?OCID=msr_researchforum_YTDescription
Explore all previous episodes: https://aka.ms/researchforumYTplaylist










