agent/papers/items/2026-2604-15579-don-t-make-models-guess-security-and-safety-symbolic-guardrails-for-domain-speci.md

Paper: Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

---

type: paper title: "Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents" authors: Yining Hong, Yining She, Eunsuk Kang, Christopher S. Timperley, Christian Kästner year: 2026 venue: arXiv url: https://arxiv.org/abs/2604.15579 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-04-16 updated_at: 2026-07-05 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• coding-agent
• tool-use methods:

benchmarks:

models:

datasets:

• cs.SE
• cs.AI
• cs.CR related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 collection_queries: agent-safety

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-safety
• inferred topics: agent-evaluation, agent-safety, coding-agent, tool-use
• arXiv categories: cs.SE, cs.AI, cs.CR
• collection score: 14

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2604.15579