Autonomous Adversary: Red-Teaming in the age of LLM

• URL: http://arxiv.org/abs/2605.06486v1
• Date: Thu, 07 May 2026 16:07:41 GMT
• Title: Autonomous Adversary: Red-Teaming in the age of LLM
• Abstract summary: Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations.<n>We analyze where these agents intersect with core offensive functions and assess current strengths and limitations.<n>We benchmark LMAs across two lateral-movement scenarios in a controlled adversary-emulation environment.
• Score: 1.4302803674538154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core enabling capability of advanced persistent threat (APT) campaigns. Using frameworks such as MITRE ATT&CK, we analyze where these agents intersect with core offensive functions and assess current strengths and limitations of LMAs with an emphasis on governance and realistic evaluation. We benchmark LMAs across two lateral-movement scenarios in a controlled adversary-emulation environment, where LMAs interact with instrumented cyber agents, observe execution artifacts, and iteratively adapt based on environmental feedback. Each scenario is formalized as an ordered task chain with explicit validation predicates, leveraging an LLM-as-a-Judge paradigm to ensure deterministic outcome verification. We compare three operational modalities: fully autonomous execution, self-scaffolded planning, and expert-defined action plans. Preliminary findings indicate that expert-defined action plans yield higher task-completion rates relative to other operational modes. However, failure remains frequent across all modalities, largely attributable to brittle command invocation, environmental and deployment instability, and recurring errors in credential management and state handling.

Related papers

• From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities [103.60384544335072]
  Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence.<n>Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities.<n> Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles.
  arXiv  Detail & Related papers  (2026-08-27T10:52:06Z)
• CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models [22.159641172687884]
  Vision-Language-Action (VLA) models have become a promising paradigm for generalist robot manipulation.<n>We propose CAC-VLA, a Context-Gated Action Conditioning framework that learns a lightweight latent-action interface directly within the VLM.<n>Experiments on LIBERO and LIBERO-Plus demonstrate the effectiveness of CAC-VLA, achieving 98.3% average success rate.
  arXiv  Detail & Related papers  (2026-07-06T08:50:05Z)
• Latent Action Reparameterization for Efficient Agent Inference [56.42014061367112]
  We propose a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior.<n>Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model.
  arXiv  Detail & Related papers  (2026-05-18T16:07:44Z)
• Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents [23.69429098915734]
  Verifier-Guided Action Selection (VegAS) is a test-time framework designed to improve robustness of MLLM-based embodied agents.<n>We show that VeGAS consistently improves generalization, achieving up to a 36% relative performance gain over strong CoT baselines.
  arXiv  Detail & Related papers  (2026-05-12T18:08:24Z)
• 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)
• Melding LLM and temporal logic for reliable human-swarm collaboration in complex scenarios [17.56189537207367]
  We introduce a neuro-symbolic framework for long-horizon human-swarm collaboration.<n>We formalize mission goals and operational rules as temporal logic formulas and admissible task orderings as task automata.<n>An event-triggered interaction protocol limits operator involvement to sparse, high-level confirmation and guidance.
  arXiv  Detail & Related papers  (2026-05-08T15:32:14Z)
• FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments [60.3427704389541]
  Large Language Models are being increasingly deployed as the decision-making core of autonomous agents.<n>Yet, in conversational benchmarks, these agents frequently fail due to the cascading effects of incorrect decision-making.<n>We present the Failure-Aware Meta-Agentic framework to tackle these challenges.
  arXiv  Detail & Related papers  (2026-04-28T02:21:53Z)
• SAND: Boosting LLM Agents with Self-Taught Action Deliberation [54.48979740613828]
  Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts.<n>We propose Self-taught ActioN Deliberation (SAND) framework, enabling LLM agents to explicitly deliberate over candidate actions before committing to one.<n>SAND achieves an average 20% improvement over initial supervised finetuning and also outperforms state-of-the-art agent tuning approaches.
  arXiv  Detail & Related papers  (2025-07-10T05:38:15Z)
• Benchmarking LLMs in an Embodied Environment for Blue Team Threat Hlunting [14.810934670172479]
  Large Language Models (LLMs) offer promising capabilities for enhancing threat analysis.<n>Their effectiveness in real-world blue team threat-hunting scenarios remains insufficiently explored.<n>We present CYBERTEAM, a benchmark designed to guide LLMs in blue teaming practice.
  arXiv  Detail & Related papers  (2025-05-17T08:33:50Z)
• SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning [2.1331883629523634]
  SagaLLM is a structured multi-agent architecture designed to address four foundational limitations of current LLM-based planning systems.<n>It bridges this gap by integrating the Saga transactional pattern with persistent memory, automated compensation, and independent validation agents.<n>It achieves significant improvements in consistency, validation accuracy, and adaptive coordination under uncertainty.
  arXiv  Detail & Related papers  (2025-03-15T01:43:03Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• DynaSaur: Large Language Agents Beyond Predefined Actions [126.98162266986554]
  Existing LLM agent systems typically select actions from a fixed and predefined set at every step.<n>We propose an LLM agent framework that can dynamically create and compose actions as needed.<n>In this framework, the agent interacts with its environment by generating and executing programs written in a general-purpose programming language.
  arXiv  Detail & Related papers  (2024-11-04T02:08:59Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)

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.