Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents

Excerpt

arXiv:2610.04156v1 Announce Type: cross Abstract: LLM agents for clinical text-to-SQL applications reason autonomously over multiple steps but cannot assess whether their own reasoning or outputs can be trusted. In high leverage applications such as healthcare, this presents a critical risk where system mistakes can be costly. These reliability failures are also resource failures: an incorrect reasoning trajectory spends computation budget on outputs that must be discarded. We introduce Sentinel