KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses
KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses
The paper proposes KPHarness, which co-evolves knowledge and probing to rewrite the external execution harness of a frozen VLA, so that it not only swaps intervention rules but also improves how it investigates failures. On mining, combat, and crafting tasks in Minecraft, it achieves broader task coverage than pure policy execution, a hand-specified fixed harness, and a version with knowledge evolution only and no adaptive probing; each harness revision is evaluated pairwise against the existing version under matched sandbox conditions and is accepted only if it shows improvement.
The paper presents a way to feed failure-diagnosis evidence into harness revision, and compares it against a fixed harness and a knowledge-evolution-only baseline.
Source: arXiv Game AI · arxiv.org