CLAIM-2026-07-31-03

The paper reports common failure patterns in which agents override policies based on contextual requests, disregard their own compliance checks, and lose procedural details across extended interactions.

Why it matters

Each pattern maps to a specific engineering control. Override defeats prompt-level policy, so the constraint belongs in the tool layer. Self-check failure defeats agent self-certification as evidence. Drift means long-horizon runs need re-anchoring, not longer prompts.

Sources

• arxiv2026handbookm