# CTI-REALM: Benchmark to Evaluate Agent Performance on Security Detection Rule Generation Capabilities

arXiv: https://arxiv.org/abs/2603.13517 · HTML: https://mlsanity.com/paper/2603.13517/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 8 of 8)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence](https://mlsanity.com/paper/2406.07599/) (2024)
- [CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning](https://mlsanity.com/paper/2509.20166/) (2025)
- [Cybersecurity AI Benchmark (CAIBench): A Meta-Benchmark for Evaluating Cybersecurity AI Agents](https://mlsanity.com/paper/2510.24317/) (2025)
- [Evaluating LLM Generated Detection Rules in Cybersecurity](https://mlsanity.com/paper/2509.16749/) (2025)
- [CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence](https://mlsanity.com/paper/2510.11974/) (2025)

## Built on by (most cited first, 4 of 4)

- [SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification](https://mlsanity.com/paper/2607.09936/) (2026)
- [Operationalizing Cyber Threat Intelligence with GraphRAG](https://mlsanity.com/paper/2608.13050/) (2026)
- [Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering](https://mlsanity.com/paper/2610.09007/) (2026)
- [Unconstrained CTI-REALM with Open-Weights](https://mlsanity.com/paper/2610.14180/) (2026)

## Abstract (arXiv)

CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is a benchmark designed to evaluate AI agents' ability to interpret cyber threat intelligence (CTI) and develop detection rules. The benchmark provides a realistic environment that replicates the security analyst workflow. This enables agents to examine CTI reports, execute queries, understand schema structures, and construct detection rules. Evaluation involves emulated attacks of varying complexity across Linux systems, cloud platforms, and Azure Kubernetes Service (AKS), with ground truth data for accurate assessment. Agent performance is measured through both final detection results and trajectory-based rewards that capture decision-making effectiveness. This work demonstrates the potential of AI agents to support labor-intensive aspects of detection engineering. Our comprehensive evaluation of 16 frontier models shows that Claude Opus 4.6 (High) achieves the highest overall reward (0.637), followed by Claude Opus 4.5 (0.624) and the GPT-5 family. An ablation study confirms that CTI-specific tools significantly improve agent performance, a variance analysis across repeated runs demonstrates result stability. Finally, a memory augmentation study shows that seeded context can close 33% of the performance gap between smaller and larger models.