Metraipolis › archive › dc_db7f136b05e8
LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment — arXiv:2608.28490
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28490
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:48:22.407Z
- SHA-256 of the archived text
1936c4f46e1d795800dd440434ca62a3b79ec3660981610290c81db67d06029f- Stable URL of this page
https://metraipolis.com/documento/dc_db7f136b05e8
How to cite
LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment — arXiv:2608.28490 — arXiv (en), https://arxiv.org/abs/2608.28490 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db7f136b05e8 (Metraipolis archive dc_db7f136b05e8, sha256 1936c4f46e1d795800dd440434ca62a3b79ec3660981610290c81db67d06029f)
BibTeX
@misc{dcdb7f136b05e8,
title = {LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment — arXiv:2608.28490},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28490},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db7f136b05e8; sha256 1936c4f46e1d795800dd440434ca62a3b79ec3660981610290c81db67d06029f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28490. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model (LLM)-based agents, which can plan, use tools, retain state, and revise actions across multi-step workflows, are being rapidly adopted to automate this work. Given the consequences of delegating security decisions to autonomous systems, understanding how such agents are built, used, and assessed is crucial. Yet to this date, there remains a lack of systematic understanding of what has been done and how far we are in this field: the term "agent" is applied inconsistently, applications differ sharply in risk, and assessment protocols are often incomparable. To gain a comprehensive and coherent view of this area hence inform relevant future research, this paper provides a systematic literature review of the (1) technical approaches, including agent architecture, perception, memory, reasoning and planning, action space, orchestration, and self-improvement, (2) applications, with respect to the security tasks served, and (3) assessment, including the datasets, outcome and trajectory metrics, safety measures, and baselines considered, over the peer-reviewed literature spanning the emergence of this area (2023--2026). Our synthesis reveals a field that has built agents able to act but not yet agents whose authority is bounded or whose behavior is auditable. In addition to knowledge systematization, we also extend our insights into the limitations of and challenges faced by current approach, application, and assessment designs, which shed light on potentially promising future research directions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.28490 — 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 2026-10-17T10:33:42.538Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).