Metraipolis › archive › dc_5effddd803fa

Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery — arXiv:2609.12216

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12216
License (as archived): CC0-1.0
Archived: 2026-10-16T03:58:06.379Z
SHA-256 of the archived text: 6ed035e18d98072ca8c8e6e3ecea265f3a40fd57dd6861cb5369bc9b776b74ef
Stable URL of this page: https://metraipolis.com/documento/dc_5effddd803fa

How to cite

Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery — arXiv:2609.12216 — arXiv (en), https://arxiv.org/abs/2609.12216 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5effddd803fa (Metraipolis archive dc_5effddd803fa, sha256 6ed035e18d98072ca8c8e6e3ecea265f3a40fd57dd6861cb5369bc9b776b74ef)

BibTeX

@misc{dc5effddd803fa,
  title = {Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery — arXiv:2609.12216},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12216},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5effddd803fa; sha256 6ed035e18d98072ca8c8e6e3ecea265f3a40fd57dd6861cb5369bc9b776b74ef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12216. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-improving agent workflows create an audit problem when the same controller can change both its behavior and the conditions under which that behavior is judged. We present GuardrailLoop, a simulation-based testbed that makes three operational contracts jointly testable: preservation of human-defined policy, compute accounting at every recorded execution prefix, and recovery of a specified scientific state after crashes. A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions; machine-directed evolution is restricted to a code-owned feature catalog and bounded knobs. The contribution is an executable boundary and an evaluation protocol that separates useful adaptation, state recovery, and repeated execution. In a paired 50-seed 2 x 2 study, round-stage growth changes target attainment by +1.00 and restricted mean compute to target by -56.97 simulated GPU-hours (95% paired-bootstrap interval [-58.91,-54.70]); idle growth has zero measured utility effect. Across 240 enumerated crash injections, all runs recover the defined outcome, but only 210 preserve the normalized trace: 30 pre-commit crashes repeat a planner call. Resource-drift, kill-switch, integrity, and output-guard matrices satisfy their specified checks. These findings show why successful outcome recovery is insufficient evidence of exactly-once execution. They establish conformance within one calibrated deterministic testbed, rather than general safety or real-world self-improvement.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.12216 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T03:44:44.700Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).