Cover Image

A Systematic Investigation of The RL-Jailbreaker in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mohammedalamen, Montaser, Roice, Kevin, McLean, Reginald, Škopac, Alyssa Lefaivre
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning to Be Cautious
by: Mohammedalamen, Montaser, et al.
Published: (2021)

Generalization in Monitored Markov Decision Processes (Mon-MDPs)
by: Mohammedalamen, Montaser, et al.
Published: (2025)

Multi-Task Reinforcement Learning Enables Parameter Scaling
by: McLean, Reginald, et al.
Published: (2025)

Meta-World+: An Improved, Standardized, RL Benchmark
by: McLean, Reginald, et al.
Published: (2025)

A New View on Planning in Online Reinforcement Learning
by: Roice, Kevin, et al.
Published: (2024)

Can Go AIs be adversarially robust?
by: Tseng, Tom, et al.
Published: (2024)

Language models are better than humans at next-token prediction
by: Shlegeris, Buck, et al.
Published: (2022)

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
by: Alakuijala, Minttu, et al.
Published: (2024)

Goal-Space Planning with Subgoal Models
by: Lo, Chunlok, et al.
Published: (2022)

$\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning
by: Kläser, Kerstin, et al.
Published: (2024)

Partial Policy Gradients for RL in LLMs
by: Mathur, Puneet, et al.
Published: (2026)

MXNorm: Reusing MXFP block scales for efficient tensor normalisation
by: McLean, Callum, et al.
Published: (2026)

RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs
by: Samineni, Soumya Rani, et al.
Published: (2025)

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
by: Zhang, Yiqi, et al.
Published: (2026)

Curiosity-driven RL for symbolic equation solving
by: O'Keeffe, Kevin P.
Published: (2025)

A Comedy of Estimators: On KL Regularization in RL Training of LLMs
by: Shah, Vedant, et al.
Published: (2025)

The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
by: Deng, Yonghong, et al.
Published: (2026)

Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
by: Su, Jingtong, et al.
Published: (2024)

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
by: Zhou, Huilin, et al.
Published: (2026)

Efficient Safety Retrofitting Against Jailbreaking for LLMs
by: Garcia-Gasulla, Dario, et al.
Published: (2025)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
by: Guo, Xingang, et al.
Published: (2024)

A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning
by: Wang, Zhe, et al.
Published: (2025)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
by: Chu, Junjie, et al.
Published: (2024)

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
by: Liu, Xiaogeng, et al.
Published: (2024)

Detecting Jailbreak Attempts in Clinical Training LLMs Through Automated Linguistic Feature Extraction
by: Nguyen, Tri, et al.
Published: (2026)

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
by: Hatgis-Kessell, Stephane, et al.
Published: (2026)

Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
by: Huang, Luke J., et al.
Published: (2026)

Monitored Markov Decision Processes
by: Parisi, Simone, et al.
Published: (2024)

Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
by: Pignatelli, Eduardo, et al.
Published: (2024)

Imbalanced Gradients in RL Post-Training of Multi-Task LLMs
by: Wu, Runzhe, et al.
Published: (2025)

Jailbreaking LLMs via Calibration
by: Lu, Yuxuan, et al.
Published: (2026)

OGBench: Benchmarking Offline Goal-Conditioned RL
by: Park, Seohong, et al.
Published: (2024)

Investigating Memory in Model-Free RL with POPGym Arcade
by: Wang, Zekang, et al.
Published: (2025)

Horizon Reduction Makes RL Scalable
by: Park, Seohong, et al.
Published: (2025)

Is Value Learning Really the Main Bottleneck in Offline RL?
by: Park, Seohong, et al.
Published: (2024)

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
by: Wen, Xuexiang, et al.
Published: (2026)

RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs
by: Hu, Ruike, et al.
Published: (2025)

Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks
by: Nurlanov, Zhakshylyk, et al.
Published: (2026)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
by: Andriushchenko, Maksym, et al.
Published: (2024)