English
Related papers

Related papers: Diverse and Effective Red Teaming with Auto-genera…

200 papers

As large language model (LLM) agents increasingly automate complex web tasks, they boost productivity while simultaneously introducing new security risks. However, relevant studies on web agent attacks remain limited. Existing red-teaming…

Artificial Intelligence · Computer Science 2026-04-02 Zheng Zhang , Jiarui He , Yuchen Cai , Deheng Ye , Peilin Zhao , Ruili Feng , Hao Wang

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Computation and Language · Computer Science 2021-04-13 Zhengxu Hou , Bang Liu , Ruihui Zhao , Zijing Ou , Yafei Liu , Xi Chen , Yefeng Zheng

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Computation and Language · Computer Science 2025-10-13 Ali Asad , Stephen Obadinma , Radin Shayanfar , Xiaodan Zhu

Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and…

Machine Learning · Computer Science 2026-03-10 Reza Refaei Afshar , Joaquin Vanschoren , Uzay Kaymak , Rui Zhang , Yaoxin Wu , Wen Song , Yingqian Zhang

Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how red-teamers' backgrounds and perspectives shape their…

Human-Computer Interaction · Computer Science 2026-05-12 Wesley Hanwen Deng , Mingxi Yan , Sunnie S. Y. Kim , Akshita Jha , Lauren Wilcox , Kenneth Holstein , Motahhare Eslami , Leon A. Gatys

The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening. Adversarial jailbreaking, the strategic manipulation of models to elicit harmful output, remains…

Machine Learning · Computer Science 2026-05-11 Montaser Mohammedalamen , Kevin Roice , Reginald McLean , Alyssa Lefaivre Škopac

The success of teams in robotics, nature, and society often depends on the division of labor among diverse specialists; however, a principled explanation for when such diversity surpasses a homogeneous team is still missing. Focusing on…

Multiagent Systems · Computer Science 2026-03-03 Michael Amir , Matteo Bettini , Amanda Prorok

Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This…

Machine Learning · Computer Science 2025-02-26 Yanshi Li , Shaopan Xiong , Gengru Chen , Xiaoyang Li , Yijia Luo , Xingyuan Bu , Yingshui Tan , Wenbo Su , Bo Zheng

Complex systems show how surprising and beautiful phenomena can emerge from structures or agents following simple rules. With the recent success of deep reinforcement learning (RL), a natural path forward would be to use the capabilities of…

Multiagent Systems · Computer Science 2021-11-30 Ted Fujimoto

Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise, requiring efficient exploration coupled with long-horizon credit assignment, and overcoming these…

Machine Learning · Computer Science 2025-10-21 Leander Diaz-Bone , Marco Bagatella , Jonas Hübotter , Andreas Krause

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Cryptography and Security · Computer Science 2025-06-10 Zifan Wang , Christina Q. Knight , Jeremy Kritz , Willow E. Primack , Julian Michael

Building autonomous machines that can explore open-ended environments, discover possible interactions and build repertoires of skills is a general objective of artificial intelligence. Developmental approaches argue that this can only be…

Machine Learning · Computer Science 2026-01-30 Cédric Colas , Tristan Karch , Olivier Sigaud , Pierre-Yves Oudeyer

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications, e.g., medical question-answering, mathematical sciences, and code generation. However, they also exhibit inherent limitations, such…

Cryptography and Security · Computer Science 2025-06-23 Yang Jiao , Xiaodong Wang , Kai Yang

Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity, undermining their utility in open-ended tasks like creative writing. Current methods lack explicit mechanisms for guiding…

Computation and Language · Computer Science 2026-01-15 Qian Cao , Yahui Liu , Wei Bi , Yi Zhao , Ruihua Song , Xiting Wang , Ruiming Tang , Guorui Zhou , Han Li

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it…

Machine Learning · Computer Science 2020-10-06 Dibya Ghosh , Abhishek Gupta , Ashwin Reddy , Justin Fu , Coline Devin , Benjamin Eysenbach , Sergey Levine

Traditionally, AI development for two-player zero-sum games has relied on two primary techniques: decision trees and reinforcement learning (RL). A common approach involves using a fixed decision tree as one player's strategy while training…

Artificial Intelligence · Computer Science 2024-12-18 Junjie Lin , Jian Zhao , Lin Liu , Yue Deng , Youpeng Zhao , Lanxiao Huang , Xia Lin , Wengang Zhou , Houqiang Li

Given a question, a language model (LM) implicitly encodes a distribution over possible answers. In practice, post-training procedures for LMs often collapse this distribution onto a single dominant mode. While this is generally not a…

Machine Learning · Computer Science 2026-03-27 Isha Puri , Mehul Damani , Idan Shenfeld , Marzyeh Ghassemi , Jacob Andreas , Yoon Kim

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Machine Learning · Computer Science 2025-05-13 Zhiqiang Wang , Ruoxi Cheng

When designing reinforcement learning (RL) agents, a designer communicates the desired agent behavior through the definition of reward functions - numerical feedback given to the agent as reward or punishment for its actions. However,…

Artificial Intelligence · Computer Science 2025-11-05 Michel Ma , Takuma Seno , Kaushik Subramanian , Peter R. Wurman , Peter Stone , Craig Sherstan

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Machine Learning · Computer Science 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin