Metraipolis › archive › dc_c5e7b9130cd6

$S^3$: Improving Agent Safety through Multi-Stage Defense — arXiv:2608.02683

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02683
License (as archived)
CC0-1.0
Archived
2026-10-31T12:17:38.932Z
SHA-256 of the archived text
36986baa689f9fdc332aa25eb3ce31bf4a867636c1924874c53a7e81048de14c
Stable URL of this page
https://metraipolis.com/documento/dc_c5e7b9130cd6

How to cite

$S^3$: Improving Agent Safety through Multi-Stage Defense — arXiv:2608.02683 — arXiv (en), https://arxiv.org/abs/2608.02683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5e7b9130cd6 (Metraipolis archive dc_c5e7b9130cd6, sha256 36986baa689f9fdc332aa25eb3ce31bf4a867636c1924874c53a7e81048de14c)
BibTeX
@misc{dcc5e7b9130cd6,
  title = {$S^3$: Improving Agent Safety through Multi-Stage Defense — arXiv:2608.02683},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02683},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5e7b9130cd6; sha256 36986baa689f9fdc332aa25eb3ce31bf4a867636c1924874c53a7e81048de14c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may emerge at different stages, propagate across steps, and become difficult to detect and mitigate. Existing safety methods protect only isolated stages and are difficult to integrate, leaving agents without comprehensive protection throughout the workflow. To address these limitations, we introduce Stage-Specific Safety Skills, a unified abstraction that represents heterogeneous safety designs as reusable and composable components with explicit stage semantics. We further develop an automated transformation pipeline that converts existing safety designs into reusable safety skills and establish a community-driven safety skill library. Building on this abstraction, we propose $S^3$, a multi-stage defense framework in which a guard agent orchestrates stage-specific safety skills for risk detection and mitigation throughout the agentic workflow. We also construct the Multi-Stage Risk Benchmark (MSRB) to evaluate representative risks across workflow stages. Experimental results show that $S^3$ consistently outperforms representative state-of-the-art baselines in both safety effectiveness and utility preservation. These results demonstrate the potential of stage-specific safety skills as a scalable and composable foundation for building resilient and trustworthy agent systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02683 — 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 2026-10-31T12:05:52.932Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).