Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage
Authors: Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun, Nikhil Kumar Dora, Manjusha Sumasadan, Sumit Kumar Tetarave, Elyson De La Cruz
Organizations: Department of Management Information Systems, University of Illinois, Springfield, USA · School of Computing and Communications, Lancaster University, United Kingdom · School of Computer Applications, Kalinga Institute of Industrial Technology, India · School of Information Technology and Artificial Intelligence, University of Cumberlands, USA
With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Security Operation Centers) analysts are often overwhelmed and struggle to analyze the huge volume of logs received from diverse devices in organizations. To address these challenges, we propose an automated and dynamic threat hunting framework for monitoring evolving threats, adapting to changing network conditions, and performing risk-based prioritization for the mitigation of suspicious and malicious traffic. By integrating Agentic AI with Splunk, an established SIEM platform, we developed a unique threat hunting framework. The framework systematically and seamlessly integrates different threat hunting modules together, ranging from traffic ingestion to anomaly assessment using a reconstruction-based autoencoder, deep reinforcement learning (DRL) with two layers for initial triage, and a large language model (LLM) for contextual analysis. We evaluated the framework against a publicly available benchmark dataset, as well as against a simulated dataset. The experimental results show that the framework can effectively adapt to different SOC objectives autonomously and identify suspicious and malicious traffic. The framework enhances operational effectiveness by supporting SOC analysts in their decision-making to block, allow, or monitor network traffic. This study thus enhances cybersecurity and threat hunting literature by presenting the novel threat hunting framework for security decision-making, as well as promoting cumulative research efforts to develop more effective frameworks to battle continuously evolving cyber threats.
Figures & tables
Threat Hunting Technique
Anomaly Assessment
Traffic Flows Prioritization
Initial Triage
Agentic AI/LLM Integration
MITRE Mapping
SIEM Integration and Validation
SOAR Suggestion
SOC Decision Support
Learned Policy adaptation
Agentic AI for Autonomous Threat Hunting Sheth et al. [2025b]
Yes
No
No
Yes
No
No
No
Yes
Partial
Agentic AI for Adaptive Threat Response Sheth et al. [2025a]
Yes
No
No
Yes
No
No
No
Yes at high-level (Partial)
Partial
Unified Framework for Human-AI Collaboration Simbian [2025] , Mohsin et al. [2025]
Conceptual
Partial
No
Yes
No
Yes at high-level
No
Yes
No
NetMon AI Framework Zambare et al. [2025]
Yes
No
Yes
Yes
No
No
No
No
No
ARGOS Agentic Detection Gu et al. [2025]
Yes
No
No
Yes
No
No
No
No
No
LLM for Threat Intelligence and Automation Tseng et al. [2024]
No
No
No
LLM integration
No
No
No
Partial
No
Table 1: Comparison between existing LLM and Agentic AI based threat hunting techniques
Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM platforms, and time-consuming manual triage workflows. We present an end-to-end threat management framework that integrates ensemble-based detection, syntax-constrained query generation, and retrieval-augmented resolution support to automate critical security workflows. Our detection module evaluates both traditional machine learning classifiers and large language models (LLMs), then combines the three best-performing LLMs to create an ensemble model, achieving 82.8% accuracy while maintaining 0.120 false positive rate on SIEM logs. We introduce the SQM (Syntax Query Metadata) architecture for automated evidence collection. It uses platform-specific syntax constraints, metadata-based retrieval, and documentation-grounded prompting to generate executable queries for IBM QRadar and Google SecOps. SQM achieves a BLEU score of 0.384 and a ROUGE-L score of 0.731. These results are more than twice as good as the baseline LLM performance. For incident resolution and recommendation generation, we demonstrate that integrating SQM-derived evidence improves resolution code prediction accuracy from 78.3% to 90.0%, with an overall recommendation quality score of 8.70. In production SOC environments, our framework reduces average incident triage time from hours to under 10 minutes. This work demonstrates that domain-constrained LLM architectures with retrieval augmentation can meet the strict reliability and efficiency requirements of operational security environments at scale.
Md Hasan Saju, Akramul Azim
† Department of Electrical, Computer and Software Engineering, Ontario Tech University, Oshawa, Ontario, Canada
We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or hints, identify the exact timestamps of malicious events. The benchmark wraps 106 real attack procedures from the OTRF Security-Datasets corpus - spanning 86 MITRE ATT&CK sub-techniques across 12 tactics - into a Gymnasium reinforcement-learning environment. Each episode presents the agent with an in-memory SQLite database of 75,000-135,000 log records produced by a deterministic campaign simulator that time-shifts and entity-obfuscates the raw recordings. The agent must iteratively submit SQL queries to discover malicious event timestamps and explicitly flag them, scored CTF-style against Sigma-rule-derived ground truth. Evaluating five frontier models - Claude Opus 4.6, GPT-5, Gemini 3.1 Pro, Kimi K2.5, and Gemini 3 Flash - on 26 campaigns covering 105 of 106 procedures, we find that all models fail dramatically: the best model (Claude Opus 4.6) submits correct flags for only 3.8% of malicious events on average, and no run across any model ever finds all flags. We define a passing score as >= 50% recall on every ATT&CK tactic - the minimum bar for unsupervised SOC deployment. No model passes: the leader clears this bar on 5 of 13 tactics and the remaining four on zero. These results suggest that current LLMs are poorly suited for open-ended, evidence-driven threat hunting despite strong performance on curated Q&A security benchmarks.
Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a multi-layered agentic AI framework that enhances SOC automation by integrating perception, anticipatory reasoning, and risk-based action planning. The proposed architecture consolidates several layers of abstraction to provide a single operational loop to support normalizing alerts, enriching context, generating hypotheses, validating structural feasibility, and executing policy-compliant responses. Conceptually evaluated within a large enterprise environment, AgentSOC improves triage consistency, anticipates attackers' intentions, and provides recommended containment options that are both operationally feasible and well-balanced between security efficacy and operational impact. The results suggest that hybrid agentic reasoning has the potential to serve as a foundation for developing adaptive, safer SOC automation in large enterprises. Additionally, a minimal Proof-Of-Concept (POC) demonstration using LANL authentication data demonstrated the feasibility of the proposed architecture.