English
Related papers

Related papers: Your Agent May Misevolve: Emergent Risks in Self-e…

200 papers

Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs).…

Cryptography and Security · Computer Science 2026-03-24 Xiaolei Zhang , Lu Zhou , Xiaogang Xu , Jiafei Wu , Tianyu Du , Heqing Huang , Hao Peng , Zhe Liu

Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of…

Artificial Intelligence · Computer Science 2026-01-15 Jian Zhang , Zhiyuan Wang , Zhangqi Wang , Yu He , Haoran Luo , li yuan , Lingling Zhang , Rui Mao , Qika Lin , Jun Liu

Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…

Artificial Intelligence · Computer Science 2026-05-13 Krti Tallam

With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round self-improving methods allow LLMs to generate…

Computation and Language · Computer Science 2024-10-31 Yi Ren , Shangmin Guo , Linlu Qiu , Bailin Wang , Danica J. Sutherland

Research on large language model (LLM) security is shifting from "will the model leak training data" to a more consequential question: can an agent with persistent, long-term memory be continuously shaped, cross-session poisoned, accessed…

Cryptography and Security · Computer Science 2026-04-21 Zehao Lin , Chunyu Li , Kai Chen

Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities. However, recent evidence indicates that LLMs can produce harmful content that violates social…

Cryptography and Security · Computer Science 2025-04-08 Xiaohan Yuan , Jinfeng Li , Dongxia Wang , Yuefeng Chen , Xiaofeng Mao , Longtao Huang , Jialuo Chen , Hui Xue , Xiaoxia Liu , Wenhai Wang , Kui Ren , Jingyi Wang

Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected,…

Machine Learning · Computer Science 2025-06-16 Edward Turner , Anna Soligo , Mia Taylor , Senthooran Rajamanoharan , Neel Nanda

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…

Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently…

Computation and Language · Computer Science 2025-09-23 Qingyu Lu , Liang Ding , Siyi Cao , Xuebo Liu , Kanjian Zhang , Jinxia Zhang , Dacheng Tao

As increasingly capable large language model (LLM)-based agents are developed, the potential harms caused by misalignment and loss of control grow correspondingly severe. To address these risks, we propose an approach that directly measures…

Computers and Society · Computer Science 2025-09-30 Seán Boddy , Joshua Joseph

The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility, cross-domain reasoning, and natural language interaction.…

Artificial Intelligence · Computer Science 2026-05-05 Guannan Liang , Qianqian Tong

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning,…

Artificial Intelligence · Computer Science 2026-05-28 Zhenyu Cui , Xiangzhong Luo

Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we introduce a dataset of 3,000…

Artificial Intelligence · Computer Science 2026-01-09 Liang Shan , Kaicheng Shen , Wen Wu , Zhenyu Ying , Chaochao Lu , Yan Teng , Jingqi Huang , Guangze Ye , Guoqing Wang , Liang He

Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters…

Machine Learning · Computer Science 2025-03-17 Leonardo Berti , Flavio Giorgi , Gjergji Kasneci

Large Language Models (LLMs) have empowered AI agents with advanced capabilities for understanding, reasoning, and interacting across diverse tasks. The addition of memory further enhances them by enabling continuity across interactions,…

Artificial Intelligence · Computer Science 2025-12-19 Himanshu Gharat , Himanshi Agrawal , Gourab K. Patro

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Artificial Intelligence · Computer Science 2025-05-30 Jen-tse Huang , Jiaxu Zhou , Tailin Jin , Xuhui Zhou , Zixi Chen , Wenxuan Wang , Youliang Yuan , Michael R. Lyu , Maarten Sap

Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining. Recent research has witnessed a transition from reinforcement learning (RL)-free to…

Computation and Language · Computer Science 2026-02-10 Xiangyuan Xue , Yifan Zhou , Guibin Zhang , Zaibin Zhang , Yijiang Li , Chen Zhang , Zhenfei Yin , Philip Torr , Wanli Ouyang , Lei Bai

The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM…

Multiagent Systems · Computer Science 2025-02-05 Jinwei Hu , Yi Dong , Shuang Ao , Zhuoyun Li , Boxuan Wang , Lokesh Singh , Guangliang Cheng , Sarvapali D. Ramchurn , Xiaowei Huang

Large Language Model-based agents have garnered significant attention and are becoming increasingly popular. Furthermore, planning ability is a crucial component of an LLM-based agent, which generally entails achieving a desired goal from…

Computation and Language · Computer Science 2025-02-07 Mengkang Hu , Pu Zhao , Can Xu , Qingfeng Sun , Jianguang Lou , Qingwei Lin , Ping Luo , Saravan Rajmohan

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

Cryptography and Security · Computer Science 2025-11-07 Chenghao Du , Quanfeng Huang , Tingxuan Tang , Zihao Wang , Adwait Nadkarni , Yue Xiao