#artificial intelligence
Jun 2026
DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making
DFAH-Bench connects replay observability to evidence, authorization, completion and cost: evidence sufficiency needs direct assessment alongside repeatability, and fixed-state probes reveal higher decision agreement alongside lower agreement with constructed policy labels.
Raffi Khatchadourian
· arXiv.org · 0 citations