English
Related papers

Related papers: The Autonomy Tax: Defense Training Breaks LLM Agen…

200 papers

With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt…

Computation and Language · Computer Science 2024-06-06 Yifei Wang , Dizhan Xue , Shengjie Zhang , Shengsheng Qian

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However,…

Multiagent Systems · Computer Science 2025-07-22 Faizan Contractor , Li Li , Ranwa Al Mallah

Reinforcement learning (RL) with outcome-based rewards has achieved significant success in training large language model (LLM) agents for complex reasoning tasks. However, in active reasoning where agents need to strategically ask questions…

Artificial Intelligence · Computer Science 2026-03-13 Deyu Zou , Yongqiang Chen , Fan Feng , Mufei Li , Pan Li , Yu Gong , James Cheng

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense…

Machine Learning · Computer Science 2023-10-23 Elizabeth Bates , Vasilios Mavroudis , Chris Hicks

Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions while real-world attacks unfold through adaptive multi-turn…

Computation and Language · Computer Science 2025-12-23 Aashray Reddy , Andrew Zagula , Nicholas Saban

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…

Artificial Intelligence · Computer Science 2026-03-10 Weize Liu , Minghui Liu , Sy-Tuyen Ho , Souradip Chakraborty , Xiyao Wang , Furong Huang

Currently, large models are prone to generating harmful content when faced with complex attack instructions, significantly reducing their defensive capabilities. To address this issue, this paper proposes a method based on constructing data…

Cryptography and Security · Computer Science 2025-01-03 Keke Zhai

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and…

Cryptography and Security · Computer Science 2024-12-03 Jing Cui , Yishi Xu , Zhewei Huang , Shuchang Zhou , Jianbin Jiao , Junge Zhang

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt…

Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational functions, including Security Operations Centers (SOCs), financial systems, and infrastructure…

Cryptography and Security · Computer Science 2026-01-06 Giuseppe Canale , Kashyap Thimmaraju

Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability assessment to incident response. Yet in operational CTI workflows, reliability gaps remain…

Cryptography and Security · Computer Science 2026-05-29 Yuqiao Meng , Luoxi Tang , Feiyang Yu , Jinyuan Jia , Guanhua Yan , Ping Yang , Zhaohan Xi

Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we…

Artificial Intelligence · Computer Science 2026-02-09 Xiaoyu Wen , Zhida He , Han Qi , Ziyu Wan , Zhongtian Ma , Ying Wen , Tianhang Zheng , Xingcheng Xu , Chaochao Lu , Qiaosheng Zhang

The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-based paradigm exhibits limitations: smaller models lack the…

Computation and Language · Computer Science 2026-05-04 Zexi Liu , Jingyi Chai , Xinyu Zhu , Shuo Tang , Rui Ye , Bo Zhang , Lei Bai , Siheng Chen

The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly…

Computation and Language · Computer Science 2024-12-18 Amir Taubenfeld , Yaniv Dover , Roi Reichart , Ariel Goldstein

Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets…

Machine Learning · Computer Science 2025-10-10 Thibaud Gloaguen , Mark Vero , Robin Staab , Martin Vechev

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Machine Learning · Computer Science 2025-10-29 Csaba Dékány , Stefan Balauca , Robin Staab , Dimitar I. Dimitrov , Martin Vechev

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Machine Learning · Computer Science 2026-03-03 Yuhui Wang , Rongyi Zhu , Ting Wang

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yangqiu Song , Bryan Hooi