Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents

arXiv:2609.28940 · cs.CR, cs.AI, cs.SE · Submitted 2026-09-24 · Read on arXiv

cs.CR, cs.AI, cs.SE

Submitted: 2026-09-24

Updated: 2026-09-24

Code: https://github.com/JoasASantos/NeuroSploit

Terminology

• Calibration — 54× in this paper · explained in 7 episodes
• Benchmark — 31× in this paper · explained in 2 episodes
• Pruning — 23× in this paper · explained in 4 episodes
• Verification — 18× in this paper · explained in 2 episodes
• Grounding — 12× in this paper · explained in 3 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Adaptation — 8× in this paper · explained in 1 episode
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Domain Adaptation — 5× in this paper · explained in 5 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Accountability — 3× in this paper · explained in 2 episodes
• Agentic AI — 3× in this paper · explained in 1 episode
• Failure Modes — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Calibration Failure — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Distribution Shift — 2× in this paper · explained in 6 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Agentic AI systems — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Arbiter — 1× in this paper · explained in 1 episode
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Federated Learning — 1× in this paper · explained in 15 episodes
• Formal Verification — 1× in this paper · explained in 2 episodes
• Introspection — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• Reinforcement Learning for Calibrated Decisions — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes

Sources

• From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation
• Multi-Agent Penetration Testing AI for the Web
• Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration Testing
• Cybersecurity AI: The Dangerous Gap Between Automation and Autonomy
• The Role of AI in Modern Penetration Testing
• Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks
• JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
• REFLEX with Jev for Efficient Selective Control in LLM Agents
• Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences
• Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
• Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)
• LLM Agents can Autonomously Exploit One-day Vulnerabilities
• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
• Constitutional AI: Harmlessness from AI Feedback
• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

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