Metraipolis › archive › dc_100f83fe0512
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing — arXiv:2608.24777
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24777
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:30:46.244Z
- SHA-256 of the archived text
93cd5ba877c6104a80272e4f66e300e4e0d8caa697b399c2c5b08fe351c8e943- Stable URL of this page
https://metraipolis.com/documento/dc_100f83fe0512
How to cite
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing — arXiv:2608.24777 — arXiv (en), https://arxiv.org/abs/2608.24777 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_100f83fe0512 (Metraipolis archive dc_100f83fe0512, sha256 93cd5ba877c6104a80272e4f66e300e4e0d8caa697b399c2c5b08fe351c8e943)
BibTeX
@misc{dc100f83fe0512,
title = {StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing — arXiv:2608.24777},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24777},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_100f83fe0512; sha256 93cd5ba877c6104a80272e4f66e300e4e0d8caa697b399c2c5b08fe351c8e943},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24777. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modification, information leakage, and unauthorized actions. Existing guardrails often evaluate completed trajectories, leaving pre-execution monitoring of step-level actions underexplored. We propose StepGuard, a step-level guard model that can audit completed agent trajectories and check tool actions before they are executed. To train StepGuard, we introduce StepGen, an automatic data engine that generates safe and unsafe trajectories with the same context but different actions at the risky step. To further reduce over-defense and under-defense, we propose Balance-GRPO, which dynamically balances learning between safe and unsafe actions based on their observed accuracy. Experiments show that StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4. When used to guard agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3% relative to the no-guard setting, while mean utility drops by only 2.8 percentage points. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CR). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2608.24777 — 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 2026-10-18T06:27:46.696Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).