works on
ai safety 1counterfactual testing 1guardrails 1hallucinated failures 1self-improving agents 1

From the 1 of 8 linked papers with an AI index.

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2026

Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened

Su Wang, Pin Qian, Yifan Lin +5

The paper investigates how self‑improving AI agents can hallucinate non‑existent failures and create unnecessary guardrails, introducing a deterministic Counterfactual Fabrication…