Metraipolis › archive › dc_c694d3bf064d
Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift — arXiv:2609.37475
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37475
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:23:55.800Z
- SHA-256 of the archived text
7e5bf21927791fbe01e57eaffa18cefac2f12c8668688aaf6e7d3e42b8c7040f- Stable URL of this page
https://metraipolis.com/documento/dc_c694d3bf064d
How to cite
Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift — arXiv:2609.37475 — arXiv (en), https://arxiv.org/abs/2609.37475 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c694d3bf064d (Metraipolis archive dc_c694d3bf064d, sha256 7e5bf21927791fbe01e57eaffa18cefac2f12c8668688aaf6e7d3e42b8c7040f)
BibTeX
@misc{dcc694d3bf064d,
title = {Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift — arXiv:2609.37475},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37475},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c694d3bf064d; sha256 7e5bf21927791fbe01e57eaffa18cefac2f12c8668688aaf6e7d3e42b8c7040f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37475. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tool-using language-model agents can decide that an action is permissible and execute it only after security-relevant state has changed. We study this proposal-to-commit gap and introduce BSC-R, a deterministic effect-boundary mechanism that binds a single-use commit authorization to the exact action and to a semantic projection of the authorization state that justified it. On 2,847 attacked AgentDojo episodes, the boundary kernel preserves the unprotected agent's behavior exactly (80.576% utility; 1.616% attack success). On 10,302 frozen proposals, it accepts every unchanged commit and rejects every instance of ten prospectively specified changed or replayed classes. In an independently generated boundary-drift experiment, full joint binding commits 0/4,403 invalid contexts while retaining 5,899/5,899 valid contexts. A prospective external evaluation on the 3,460-scenario CONTINUITY suite retains all 700 benign cases, prevents 1,200/1,200 represented non-replay invalid effects, handles 160/160 replay lifecycles correctly, and withholds 200/200 ambiguous no-release cases. The broader external suite also exposes the method's limit: across all 2,560 attacks, BSC-R has a 25% invalid-effect commit rate versus 0% for CONTINUITY. The result is therefore a scoped commit-time consistency mechanism, not a universal agent-safety claim. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.37475 — 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 2026-10-07T15:54:53.633Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).