Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement

[2608.14590] Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14590 (cs) [Submitted on 22 Jun 2026] Title: Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement Authors: Pierre Dantas , Lucas Cordeiro , Ehsan Nowroozi , Tihanyi Norbert View a PDF of the paper titled Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement, by Pierre Dantas and 3 other authors View PDF HTML (experimental) Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools. However, no existing system provides formally grounded, task-level safety guarantees for the plans these agents generate. Research remains fragmented across specification, verification, and enforcement, limiting understanding of the strengths and limitations of existing approaches. To address this gap, we conducted a PRISMA 2020 systematic review of 38 studies published between 2022 and 2026 and retrieved from six academic databases. Our analysis reveals four key findings. First, the specification bottleneck remains the primary challenge: natural-language-to-formal translation achieves only 24% to 35% semantic correctness, undermining downstream verification. Second, runtime monitoring is the most mature enforcement strategy, reducing unsafe actions by 40% to 65% in controlled settings, but it does not provide complete safety guarantees. Third, the verifier tax shows that blocking 94% of unsafe actions can still result in less than 5% safe task completion because agents exploit alternative unsafe paths. Finally, no existing approach simultaneously achieves soundness, scalability, semantic correctness, and task-level safety preservation. We contribute a three-level taxonomy, a comparative analysis of existing techniques, a synthesis of evidence on the verifier tax, and a ten-problem research agenda for trustworthy agentic AI. Comments: 28 pages Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2608.14590 [cs.AI] (or arXiv:2608.14590v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14590 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Pierre Dantas [ view email ] [v1] Mon, 22 Jun 2026 21:03:26 UTC (88 KB) Full-text links: Access Paper: View a PDF of the paper titled Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement, by Pierre Dantas and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement#610092
• ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools#618522
• ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents#405550
• PVDetector: Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents through Policy-Violation Concept Analysis#366195
• DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection#394342