Metraipolis › archive › dc_fb71cd725a24
Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay — arXiv:2610.01138
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01138
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:03:58.617Z
- SHA-256 of the archived text
2be4161b98234325c7c9ab2274f42119870efb669f172b66d079bce1ece10626- Stable URL of this page
https://metraipolis.com/documento/dc_fb71cd725a24
How to cite
Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay — arXiv:2610.01138 — arXiv (en), https://arxiv.org/abs/2610.01138 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb71cd725a24 (Metraipolis archive dc_fb71cd725a24, sha256 2be4161b98234325c7c9ab2274f42119870efb669f172b66d079bce1ece10626)
BibTeX
@misc{dcfb71cd725a24,
title = {Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay — arXiv:2610.01138},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01138},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb71cd725a24; sha256 2be4161b98234325c7c9ab2274f42119870efb669f172b66d079bce1ece10626},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01138. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement policies are tested in 28,800 exhaustive permutation trials and 2,160 scripted multistep episodes. Joint policies are spatially order-invariant conditional on fixed priorities, yet conservative rejection completes only 31.25% of agents in a six-agent doorway task versus 90.28% for random tickets; the paired improvement is 59.03 percentage points (95% bootstrap interval: 50.00-68.06). All policies preserve the tested spatial constraints, and priority arbitration still misses the independent small-instance optimum. A separate full-state journal audit exactly replays 156 checkpoints and rejects 1,332 constructed corruptions with a retained terminal anchor. The evidence concerns execution semantics, not human realism or long-run fairness. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.01138 — 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 2026-10-06T10:21:27.918Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).