# COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies

arXiv: https://arxiv.org/abs/2606.30479 · HTML: https://mlsanity.com/paper/2606.30479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 62 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Deep Reinforcement Learning for Cyber Security](https://mlsanity.com/paper/1906.05799/) (2019)
- [CybORG: A Gym for the Development of Autonomous Cyber Agents](https://mlsanity.com/paper/2108.09118/) (2021)
- [Network Environment Design for Autonomous Cyberdefense](https://mlsanity.com/paper/2103.07583/) (2021)
- [NASimEmu: Network Attack Simulator & Emulator for Training Agents Generalizing to Novel Scenarios](https://mlsanity.com/paper/2305.17246/) (2023)
- [Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games](https://mlsanity.com/paper/2403.17674/) (2024)
- [Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments](https://mlsanity.com/paper/2308.12086/) (2023)
- [Large Language Models are Autonomous Cyber Defenders](https://mlsanity.com/paper/2505.04843/) (2025)
- [Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides](https://mlsanity.com/paper/2402.17531/) (2024)
- [Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search](https://mlsanity.com/paper/2407.11070/) (2024)
- [CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents](https://mlsanity.com/paper/2410.16324/) (2024)
- [A Multi-Vocal Review of Security Orchestration](https://mlsanity.com/paper/2002.09190/) (2020)
- [Cyber Sentinel: Exploring Conversational Agents in Streamlining Security Tasks with GPT-4](https://mlsanity.com/paper/2309.16422/) (2023)
- [CyberAlly: Leveraging LLMs and Knowledge Graphs to Empower Cyber Defenders](https://mlsanity.com/paper/2504.07457/) (2025)
- [A Survey on Enterprise Network Security: Asset Behavioral Monitoring and Distributed Attack Detection](https://mlsanity.com/paper/2306.16675/) (2023)
- [Multi-Agent Actor-Critics in Autonomous Cyber Defense](https://mlsanity.com/paper/2410.09134/) (2024)

## Abstract (arXiv)

Mitigating an observed adversary in an enterprise network typically takes weeks of expert work: an analyst derives a mitigation tailored to that adversary, validates it without breaking production, and verifies it disrupts the specific attack. The procedure relies on expert judgment and cannot safely be exercised against the production network. COHORT is the first end-to-end framework to automate this procedure for deployable mitigations. A role-decomposed multi-agent LLM workflow proposes candidates, implements them as real device commands, and refines them through a critique loop, all on a high-fidelity GNS3 emulator running real vendor firmware (firewall, switch, router). Each candidate is evaluated by offensive replay: re-executing the original adversary on the mitigated network for a paired comparison against the unmitigated baseline, rather than the reward-signal or expert-judgment proxies used in prior simulation, hybrid, and configuration-generation work. Two further checks complement replay: a connectivity-regression check (LAN ping and internet HTTP probe) rejects mitigations that disrupt legitimate LAN or internet connectivity, and a cumulative evaluation stacks approved mitigations onto a persistent state to surface compound effects. Across three topologies and four attack scenarios (ransomware, lateral movement, DNS exfiltration, data theft), 46.7% of generated mitigations both disrupt the attack and preserve connectivity under replay, 4.4 times the rate of a single-agent baseline using the same model and tool access. A demo video walking through the framework is available with our released artifacts.