HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents

arXiv:2609.33446 · cs.CR, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/lzwhehe/HESP

Terminology

• Verifier — 12× in this paper · explained in 2 episodes
• Provenance — 7× in this paper · explained in 3 episodes
• Information Gain — 6× in this paper · explained in 2 episodes
• Active Learning — 2× in this paper · explained in 6 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• International Conference on Learning Representations — 2× in this paper
• Network and Distributed System Security Symposium — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Active Learning Strategy — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Alert Fatigue — 1× in this paper · explained in 1 episode
• Quantization — 1× in this paper · explained in 12 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
• AI-Driven Guided Response for Security Operation Centers with Microsoft Copilot for Security
• Progent: Securing AI Agents with Privilege Control
• Language Models (Mostly) Know What They Know

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs