Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

• URL: http://arxiv.org/abs/2603.10041v1
• Date: Fri, 06 Mar 2026 22:24:37 GMT
• Title: Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents
• Abstract summary: We study how autonomous offensive agents fail to transfer beyond the networks on which they are trained.<n>We compare three agent families (traditional RL, adaptation agents, and LLM-based agents) and use action-distribution-based behavioral/XAI analyses to localize failure modes.<n> prompt-driven LLM agents achieve the highest success on the held-out reassignment, but at the cost of increased inference-time compute, reduced transparency, and practical failure modes such as repetition/invalid-action loops.
• Score: 0.5611004142746667
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift -- unseen host/subnet IP reassignment in an otherwise fixed enterprise scenario -- and evaluate attacker generalization in the NetSecGame environment. Agents are trained on five IP-range variants and tested on a sixth unseen variant; only the meta-learning agent may adapt at test time. We compare three agent families (traditional RL, adaptation agents, and LLM-based agents) and use action-distribution-based behavioral/XAI analyses to localize failure modes. Some adaptation methods show partial transfer but significant degradation under unseen reassignment, indicating that even address-space changes can break long-horizon attack policies. Under our evaluation protocol and agent-specific assumptions, prompt-driven pretrained LLM agents achieve the highest success on the held-out reassignment, but at the cost of increased inference-time compute, reduced transparency, and practical failure modes such as repetition/invalid-action loops.

Related papers

• Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference [7.174851769918924]
  Large language model (LLM) agents can reason over operational context but may hallucinate attacks and responses.<n>We present a hierarchical agentic response framework that integrates LLM-based attack inference, rollout planning, and digital-twin validation.<n>We evaluate the framework on a 33-component enterprise-network testbed under three multi-stage attack scenarios.
  arXiv  Detail & Related papers  (2026-08-15T04:01:27Z)
• Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution [25.26084224278813]
  Role-Agent harnesses a single Large Language Model (LLM) to function concurrently as both the agent and the environment.<n>Role-Agent consistently improves performance, yielding an average gain of over 4% over strong baselines.
  arXiv  Detail & Related papers  (2026-06-09T14:28:07Z)
• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly [15.168064055560293]
  We introduce textscCyberEvolver, a self-evolving cybersecurity agent framework.<n>textscCyberEvolver iteratively revises its own scaffold based on experience from failed execution attempts.<n>We evaluate textscCyberEvolver on CTF challenges, vulnerability exploitation, and penetration-testing tasks using four open-source LLMs.
  arXiv  Detail & Related papers  (2026-05-25T16:26:59Z)
• OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents [74.20327254615854]
  Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks.<n>Existing inference-time adaptation methods for LLM agents mainly rely on prompting or retrieval.<n>We propose OLIVIA, an inference-time action adaptation framework for ReAct-style agents.
  arXiv  Detail & Related papers  (2026-05-11T19:28:20Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Free Agent in Agent-Based Mixture-of-Experts Generative AI Framework [0.0]
  Reinforcement Learning Free Agent (RLFA) algorithm introduces a reward-based mechanism to detect and remove agents exhibiting persistent underperformance.<n>A primary use case is fraud detection, where RLFA promptly swaps out an agent whose detection accuracy dips below a preset threshold.<n>This dynamic, free-agency cycle ensures sustained accuracy, quicker adaptation to emerging threats, and minimal disruption to ongoing operations.
  arXiv  Detail & Related papers  (2025-01-29T13:00:22Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories [88.08381083207449]
  We show the prevalence of emphgeneralization failure on controllable states from stranger agents. We propose a novel method called Self-Trajectory Augmentation (STA), which will reset the environment to the agent's old states according to the Q function during training.
  arXiv  Detail & Related papers  (2023-04-26T10:12:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.