{"total":60,"rows":[{"id":"2207.12355","title":"Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation","created":"2022-07-25","cited_by_count":37,"area":null},{"id":"2211.15557","title":"Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2303.04926","title":"Automated Cyber Defence: A Review","created":"2023-03-08","cited_by_count":21,"area":null},{"id":"2305.17246","title":"NASimEmu: Network Attack Simulator & Emulator for Training Agents Generalizing to Novel Scenarios","created":"2023-05-26","cited_by_count":20,"area":null},{"id":"2403.17674","title":"Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games","created":"2024-03-26","cited_by_count":20,"area":"agents"},{"id":"2111.00289","title":"Intrusion Prevention through Optimal Stopping","created":"2021-10-30","cited_by_count":18,"area":null},{"id":"2308.12086","title":"Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2306.09318","title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2301.06085","title":"Learning Near-Optimal Intrusion Responses Against Dynamic Attackers","created":"2023-01-11","cited_by_count":15,"area":null},{"id":"2409.18197","title":"Autonomous Network Defence using Reinforcement Learning","created":"2024-09-26","cited_by_count":15,"area":"deeprl"},{"id":"2505.04843","title":"Large Language Models are Autonomous Cyber Defenders","created":"2025-05-07","cited_by_count":15,"area":null},{"id":"2310.05939","title":"Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning","created":"2023-08-25","cited_by_count":12,"area":null},{"id":"2407.11070","title":"Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search","created":"2024-07-12","cited_by_count":12,"area":null},{"id":"2410.16324","title":"CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents","created":"2024-10-18","cited_by_count":11,"area":"deeprl"},{"id":"2410.17647","title":"Entity-based Reinforcement Learning for Autonomous Cyber Defence","created":"2024-10-23","cited_by_count":11,"area":"deeprl"},{"id":"2508.05188","title":"Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2312.04940","title":"Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning","created":"2023-12-08","cited_by_count":9,"area":null},{"id":"2304.11052","title":"A Multiagent CyberBattleSim for RL Cyber Operation Agents","created":"2023-04-03","cited_by_count":8,"area":null},{"id":"2407.05775","title":"Structural Generalization in Autonomous Cyber Incident Response with Message-Passing Neural Networks and Reinforcement Learning","created":"2024-07-08","cited_by_count":7,"area":"deeprl"},{"id":"2205.14694","title":"Learning Security Strategies through Game Play and Optimal Stopping","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2412.18442","title":"SoK: On the Offensive Potential of AI","created":"2024-12-24","cited_by_count":5,"area":null},{"id":"2604.15590","title":"CSLE: A Reinforcement Learning Platform for Autonomous Security Management","created":"2026-04-16","cited_by_count":5,"area":"deeprl"},{"id":"2111.11932","title":"Modelling Direct Messaging Networks with Multiple Recipients for Cyber Deception","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2410.16383","title":"Designing Robust Cyber-Defense Agents with Evolving Behavior Trees","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2301.04299","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2304.01366","title":"Enabling A Network AI Gym for Autonomous Cyber Agents","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2304.11084","title":"Training Automated Defense Strategies Using Graph-based Cyber Attack Simulations","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2404.10788","title":"The Path To Autonomous Cyber Defense","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2407.15656","title":"Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN","created":"2024-07-22","cited_by_count":3,"area":"deeprl"},{"id":"2412.02875","title":"Out-of-Distribution Detection for Neurosymbolic Autonomous Cyber Agents","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2509.06539","title":"Learning Optimal Defender Strategies for CAGE-2 using a POMDP Model","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2602.04809","title":"Beyond Rewards in Reinforcement Learning for Cyber Defence","created":"2026-02-04","cited_by_count":3,"area":"deeprl"},{"id":"2604.08805","title":"Building Better Environments for Autonomous Cyber Defence","created":"2026-04-09","cited_by_count":3,"area":"deeprl"},{"id":"2208.07127","title":"Deception for Cyber Defence: Challenges and Opportunities","created":"2022-08-15","cited_by_count":2,"area":null},{"id":"2401.10149","title":"Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security","created":"2024-01-18","cited_by_count":2,"area":null},{"id":"2410.09134","title":"Multi-Agent Actor-Critics in Autonomous Cyber Defense","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2509.20008","title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation","created":"2025-09-24","cited_by_count":2,"area":"deeprl"},{"id":"2304.01244","title":"Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents","created":"2023-04-03","cited_by_count":1,"area":null},{"id":"2503.02780","title":"Quantitative Resilience Modeling for Autonomous Cyber Defense","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2505.22531","title":"Training RL Agents for Multi-Objective Network Defense Tasks","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2511.09114","title":"Towards a Generalisable Cyber Defence Agent for Real-World Computer Networks","created":"2025-11-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.16205","title":"Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.16233","title":"FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2412.02016","title":"Explore Reinforced: Equilibrium Approximation with Reinforcement Learning","created":"2024-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2503.23615","title":"An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2508.19488","title":"PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.10983","title":"Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions","created":"2025-09-13","cited_by_count":0,"area":"deeprl"},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.20279","title":"Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.08168","title":"Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.13621","title":"Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.13832","title":"Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.16236","title":"Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.18223","title":"Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents","created":"2026-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2606.30479","title":"COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.11852","title":"BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.16563","title":"The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19399","title":"Efficient Nash Equilibrium Computation for Cybersecurity Games","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.00759","title":"Crossing the Cyber Divide: Sim-to-Sim and Sim-to-Real Transfer for RL Agents","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.18594","title":"Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}