Metraipolis › archive › dc_7378f33d4e0d
Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault — arXiv:2609.32802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32802
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:56:08.198Z
- SHA-256 of the archived text
2612324c581895106f7b93490b2e5d112da8f5fd948a294488d753389b20b610- Stable URL of this page
https://metraipolis.com/documento/dc_7378f33d4e0d
How to cite
Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault — arXiv:2609.32802 — arXiv (en), https://arxiv.org/abs/2609.32802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7378f33d4e0d (Metraipolis archive dc_7378f33d4e0d, sha256 2612324c581895106f7b93490b2e5d112da8f5fd948a294488d753389b20b610)
BibTeX
@misc{dc7378f33d4e0d,
title = {Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault — arXiv:2609.32802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7378f33d4e0d; sha256 2612324c581895106f7b93490b2e5d112da8f5fd948a294488d753389b20b610},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
One variable sets what an upstream fault costs a staged pipeline of language-model agents: re-derivability, how much of what a stage needs it can rebuild from the original problem. Grounding an inspector agent in that problem is worth +0.608 [+0.517, +0.700] to +0.358 over a blind one on four open-weight backbones served with thinking disabled, and on the two Qwen backbones the blind inspector changes no item at all. That head-to-head is exploratory. One deterministic fault enters the first stage, and we re-expose the original problem to $k = 0,\dots,3$ of the downstream stages with agents, items, fault and topology held fixed, on 120 gsm_hard items per arm at temperature zero. Accuracy under fault rises on four of four backbones, from +0.233 to +0.392, the largest Holm-adjusted $p$ being $2.1\times10^{-6}$. A registered kill test rules out tokens. Blanking every word holds the word slots fixed, and retention tracks the visible fraction on four of four, climbing from 0.221 to 0.692 on the primary. Those two families are confirmatory and everything else here is exploratory. The interaction excludes zero on two of four backbones under the registered pipeline, four of four under a three-stage pipeline, and three of four under full message history, the primary at +0.317. On Llama-3.1-8B the fault carries no detectable cost at any dose, so the other three carry every claim about what a fault costs. Re-derivability also sets what the architecture costs, and no decomposition we measured reliably beats one direct call. With no fault injected the registered pipeline loses to that call by -0.267, -0.125 and -0.317, and on Phi-4 reads +0.058 at $p = 0.118$, which the test fails to separate from zero. The repair that works is cheap and front-loaded: the first re-grounded stage buys +0.394 of matched retention for +59.8 tokens per item on Qwen3-14B, and the stages after it buy nothing.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32802 — 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 2026-10-07T20:29:00.988Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).