# Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.05466 · HTML: https://mlsanity.com/paper/2601.05466/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 33 of its 36 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction](https://mlsanity.com/paper/2402.18104/) (2024)
- [FlipAttack: Jailbreak LLMs via Flipping](https://mlsanity.com/paper/2410.02832/) (2024)
- [ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors](https://mlsanity.com/paper/2402.16444/) (2024)
- [WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response](https://mlsanity.com/paper/2405.14023/) (2024)
- [Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries](https://mlsanity.com/paper/2405.20653/) (2024)
- [RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs](https://mlsanity.com/paper/2406.08725/) (2024)

## Built on by (most cited first, 2 of 2)

- [SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks](https://mlsanity.com/paper/2608.01117/) (2026)
- [Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces](https://mlsanity.com/paper/2607.00481/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, however, they remain critically vulnerable to jailbreak attacks that elicit harmful responses violating human values and safety guidelines. Despite extensive research on defense mechanisms, existing safeguards prove insufficient against sophisticated adversarial strategies. In this work, we propose iMIST (underlineinteractive underlineMulti-step underlineProgreunderlinessive underlineTool-disguised Jailbreak Attack), a novel adaptive jailbreak method that synergistically exploits vulnerabilities in current defense mechanisms. iMIST disguises malicious queries as normal tool invocations to bypass content filters, while simultaneously introducing an interactive progressive optimization algorithm that dynamically escalates response harmfulness through multi-turn dialogues guided by real-time harmfulness assessment. Our experiments on widely-used models demonstrate that iMIST achieves higher attack effectiveness, while maintaining low rejection rates. These results reveal critical vulnerabilities in current LLM safety mechanisms and underscore the urgent need for more robust defense strategies.