Assess portability of the habituation scheduler beyond the evaluated scanner and benchmark setting

Determine whether the reward-free mushroom-body-inspired habituation scheduler's reduction of repeated tool-and-URL selections generalizes to other scanners, production-scale security-testing surfaces, and LLM-controlled action-selection loops.

Background

The reported scheduling result was obtained with one scanner, its specific candidate-frontier discipline, and local benchmark laboratories. The confirmatory evidence therefore establishes a bounded result for that experimental setting rather than broad external validity.

The paper explicitly states that portability to other scanners, production-scale surfaces, and LLM-controlled selection loops remains untested. Establishing such portability would determine whether the observed repetition-control effect is specific to the evaluated implementation or transfers to materially different deployment contexts.

References

The scheduling result uses one scanner and its frontier discipline; portability to other scanners, production-scale surfaces, or an LLM-controlled selection loop remains untested.

— The Fly That Stopped: Mushroom-Body-Inspired Habituation as a Reward-Free Scheduling Prior for Autonomous Penetration Testing  (2609.29126 - Moutesidis, 24 Sep 2026) in Section 8, “Discussion and Limitations,” subsection “External validity and complementary experiments”