Multi-Agent LLM Governance for Safe Two-Timescale Reinforcement Learning in SDN-IoT Defense

• URL: http://arxiv.org/abs/2604.01127v1
• Date: Wed, 01 Apr 2026 16:48:03 GMT
• Title: Multi-Agent LLM Governance for Safe Two-Timescale Reinforcement Learning in SDN-IoT Defense
• Abstract summary: Software-Defined Networking (SDN) is increasingly adopted to secure Internet-of-Things (IoT) networks.<n> mitigation actions impact controller workload, queue dynamics, rule-installation delay, and future traffic observations.<n>This paper introduces a self-reflective two-timescale solution separating fast mitigation from slow policy governance.
• Score: 5.351146356849584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Software-Defined Networking (SDN) is increasingly adopted to secure Internet-of-Things (IoT) networks due to its centralized control and programmable forwarding. However, SDN-IoT defense is inherently a closed-loop control problem in which mitigation actions impact controller workload, queue dynamics, rule-installation delay, and future traffic observations. Aggressive mitigation may destabilize the control plane, degrade Quality of Service (QoS), and amplify systemic risk. Existing learning-based approaches prioritize detection accuracy while neglecting controller coupling and short-horizon Reinforcement Learning (RL) optimization without structured, auditable policy evolution. This paper introduces a self-reflective two-timescale SDN-IoT defense solution separating fast mitigation from slow policy governance. At the fast timescale, per-switch Proximal Policy Optimization (PPO) agents perform controller-aware mitigation under safety constraints and action masking. At the slow timescale, a multi-agent Large Language Model (LLM) governance engine generates machine-parsable updates to the global policy constitution Pi, which encodes admissible actions, safety thresholds, and reward priorities. Updates (Delta Pi) are validated through stress testing and deployed only with non-regression and safety guarantees, ensuring an auditable evolution without retraining RL agents. Evaluation under heterogeneous IoT traffic and adversarial stress shows improvements of 9.1% Macro-F1 over PPO and 15.4% over static baselines. Worst-case degradation drops by 36.8%, controller backlog peaks by 42.7%, and RTT p95 inflation remains below 5.8% under high-intensity attacks. Policy evolution converges within five cycles, reducing catastrophic overload from 11.6% to 2.3%.

Related papers

• Knowledge-Distilled End-to-End Reinforcement Learning for Smooth 6-DOF Thrust Control and Rapid Adaptation to Ocean Currents in Remotely Operated Vehicles [16.40999985739862]
  This paper proposes the thrust rapid current adaptation policy optimization (TSRCA-PPO) method which learns a near-optimal strategy by a twostage distillation learning framework.<n> Simulation results demonstrate that the proposed TSRCA-PPO method consistently outperforms the conventional cascaded P-PID controller.
  arXiv  Detail & Related papers  (2026-08-09T09:23:15Z)
• MA-HEAD-Net: Adaptive Rule-Guided Multi-Agent DRL for AoI Minimization in UAV-Assisted Emergency Networks [71.01350912967922]
  In post-disaster scenarios, unmanned aerial vehicles (UAVs) are critical for establishing emergency communication networks.<n>This paper investigates age of information (AoI) minimization for UAV-assisted emergency communications with heterogeneous emergency services.<n>We develop MA-HEAD-Net, an adaptive rule-guided multi-agent deep reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-08-02T10:05:50Z)
• Adaptive Security at the Edge for 6G-Enabled Healthcare IoT [1.1331039764827395]
  We present a kernel-plane closed-loop controller that observes per-source traffic intensity at the edge and enforces an auditable, multi-tier rate policy.<n>We show that adaptive, auditable enforcement at the gateway can improve healthcare IoT, and it can be extended toward on-demand policy deployment.
  arXiv  Detail & Related papers  (2026-07-30T08:34:42Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data [49.370849653460716]
  We propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation signal as an automated early-stopping mechanism.<n> evaluated on 25 continuous control tasks from the Minari benchmark suite.<n>SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x.
  arXiv  Detail & Related papers  (2026-05-07T08:32:09Z)
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing [79.88256756334327]
  Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision.<n>We propose Sample-Routed Policy Optimization (SRPO)<n>SRPO routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction.
  arXiv  Detail & Related papers  (2026-04-02T17:29:18Z)
• A Safety-Constrained Reinforcement Learning Framework for Reliable Wireless Autonomy [1.5469452301122173]
  We propose a proactive safety-constrained RL framework that integrates proof-carrying control with empowerment-budgeted (EB) enforcement.<n>Our method achieves provable safety guarantees with minimal performance degradation.<n>Results highlight the potential of proactive safety constrained RL to enable trustworthy wireless autonomy in future 6G networks.
  arXiv  Detail & Related papers  (2026-01-12T02:02:52Z)
• Proactive DDoS Detection and Mitigation in Decentralized Software-Defined Networking via Port-Level Monitoring and Zero-Training Large Language Models [3.6260109722491465]
  Software-Defined Networking (cSDN) offers flexible and programmable control of networks but suffers from scalability and reliability issues.<n>Decentralized SDN (dSDN) Distributed alleviates these concerns by distributing control across multiple local controllers.<n>This architecture remains highly vulnerable to Denial-of-Service (DDoS) attacks.<n>We propose a novel detection and mitigation framework tailored for dSDN environments.
  arXiv  Detail & Related papers  (2025-11-01T08:57:29Z)
• GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping [63.33669214116784]
  GRPO-Guard is a simple yet effective enhancement to existing GRPO frameworks.<n>It restores a balanced and step-consistent importance ratio, ensuring that PPO clipping properly constrains harmful updates.<n>It substantially mitigates implicit over-optimization without relying on heavy KL regularization.
  arXiv  Detail & Related papers  (2025-10-25T14:51:17Z)
• Agentic Entropy-Balanced Policy Optimization [114.90524574220764]
  Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents.<n>While RL algorithms autonomously explore high-uncertainty tool-call steps under the guidance of entropy, excessive reliance on entropy signals can impose further constraints.<n>We propose the Agentic Entropy-Balanced Policy Optimization (AEPO), an agentic RL algorithm designed to balance entropy in both the rollout and policy update phases.
  arXiv  Detail & Related papers  (2025-10-16T10:40:52Z)
• Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning [45.51804571136028]
  Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs)<n>We introduce Slow-Fast Policy Optimization (SFPO), a simple yet efficient framework to address these limitations via decomposing each step into three stages.<n>SFPO consistently improves stability, reduces rollouts, and accelerates convergence of reasoning RL training.
  arXiv  Detail & Related papers  (2025-10-05T07:22:54Z)
• 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)
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations [88.94162416324505]
  A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is ineffective for many RL tasks.
  arXiv  Detail & Related papers  (2020-03-19T17:59:59Z)

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.