English
Related papers

Related papers: Adversarial Reinforcement Learning for Large Langu…

200 papers

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous…

Machine Learning · Computer Science 2026-02-10 Dilip Arumugam , Thomas L. Griffiths

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Artificial Intelligence · Computer Science 2026-01-08 Kanghua Mo , Li Hu , Yucheng Long , Zhihao Li

Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no…

Machine Learning · Computer Science 2023-09-14 Zeyang Li , Chuxiong Hu , Yunan Wang , Yujie Yang , Shengbo Eben Li

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-08 Zheyue Tan , Mustapha Abdullahi , Tuo Shi , Huining Yuan , Zelai Xu , Chao Yu , Boxun Li , Bo Zhao

Modern algorithms in the domain of Deep Reinforcement Learning (DRL) demonstrated remarkable successes; most widely known are those in game-based scenarios, from ATARI video games to Go and the StarCraft~\textsc{II} real-time strategy game.…

Artificial Intelligence · Computer Science 2020-05-29 Eric MSP Veith , Nils Wenninghoff , Emilie Frost

Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where…

Cryptography and Security · Computer Science 2026-01-16 Hao Li , Yankai Yang , G. Edward Suh , Ning Zhang , Chaowei Xiao

Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based approaches fail to generalize since: (a) the gap between…

Machine Learning · Computer Science 2017-03-09 Lerrel Pinto , James Davidson , Rahul Sukthankar , Abhinav Gupta

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

Artificial Intelligence · Computer Science 2025-08-06 Xufang Luo , Yuge Zhang , Zhiyuan He , Zilong Wang , Siyun Zhao , Dongsheng Li , Luna K. Qiu , Yuqing Yang

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…

Machine Learning · Computer Science 2024-06-04 Frank Weizhen Liu , Chenhui Hu

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

Cryptography and Security · Computer Science 2025-07-30 Stephen Casper , Lennart Schulze , Oam Patel , Dylan Hadfield-Menell

Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn…

Cryptography and Security · Computer Science 2025-10-22 Shiyi Yang , Zhibo Hu , Xinshu Li , Chen Wang , Tong Yu , Xiwei Xu , Liming Zhu , Lina Yao

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

Cryptography and Security · Computer Science 2026-05-28 Xiang Fang , Wanlong Fang

Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a safety classifier, a computational…

Computation and Language · Computer Science 2023-11-02 Jinhwa Kim , Ali Derakhshan , Ian G. Harris

This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and…

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Machine Learning · Computer Science 2024-05-16 Xingzhou Lou , Junge Zhang , Ziyan Wang , Kaiqi Huang , Yali Du

We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, the adversary aims…

Machine Learning · Computer Science 2019-11-14 Yen-Chen Lin , Zhang-Wei Hong , Yuan-Hong Liao , Meng-Li Shih , Ming-Yu Liu , Min Sun

This work proposes a novel technique Augmented Reinforcement Learning framework for the improvement of decision-making capabilities of machine learning models. The introduction of agents as external overseers checks on model decisions. The…

Machine Learning · Computer Science 2025-08-05 Sandesh Kumar Singh

Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this integration also introduces new security vulnerabilities,…

Cryptography and Security · Computer Science 2025-06-17 Haowei Wang , Rupeng Zhang , Junjie Wang , Mingyang Li , Yuekai Huang , Dandan Wang , Qing Wang

Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed. However, the possibility and feasibility of such attacks against Deep Reinforcement Learning…

Cryptography and Security · Computer Science 2020-05-15 Jianwen Sun , Tianwei Zhang , Xiaofei Xie , Lei Ma , Yan Zheng , Kangjie Chen , Yang Liu