English
Related papers

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

200 papers

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…

Cryptography and Security · Computer Science 2026-05-12 Ziwen Cai , Yihe Zhang , Xiali Hei

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…

Computation and Language · Computer Science 2026-02-10 Weixiang Zhao , Yingshuo Wang , Yichen Zhang , Yang Deng , Yanyan Zhao , Wanxiang Che , Bing Qin , Ting Liu

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Artificial Intelligence · Computer Science 2025-08-20 Yuzhi Tang , Tianxiao Li , Elizabeth Li , Chris J. Maddison , Honghua Dong , Yangjun Ruan

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…

Artificial Intelligence · Computer Science 2026-05-12 Ye Yu , Xiaopeng Yuan , Haibo Jin , Heming Liu , Yaoning Yu , Haohan Wang

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

Machine Learning · Computer Science 2025-07-08 Jeremiah Giordani

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…

Artificial Intelligence · Computer Science 2026-05-12 Zhiyuan Fan , Wenwei Jin , Feng Zhang , Bin Li , Yihong Dong , Yao Hu , Jiawei Li

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Cryptography and Security · Computer Science 2025-05-20 Wenrui Xu , Keshab K. Parhi

Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolution techniques. However, in large-scale industrial settings…

Computation and Language · Computer Science 2026-04-21 Chenglong Wang , Canjia Li , Xingzhao Zhu , Yifu Huo , Huiyu Wang , Weixiong Lin , Yun Yang , Qiaozhi He , Tianhua Zhou , Xiaojia Chang , Jingbo Zhu , Tong Xiao

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

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

Large Language Model (LLM) agents are increasingly deployed to automate complex workflows in mobile and desktop environments. However, current model-centric agent architectures struggle to self-evolve post-deployment: improving…

Artificial Intelligence · Computer Science 2025-12-19 Zibin Liu , Cheng Zhang , Xi Zhao , Yunfei Feng , Bingyu Bai , Dahu Feng , Erhu Feng , Yubin Xia , Haibo Chen

With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and…

Cryptography and Security · Computer Science 2025-09-22 Shang Wang , Tianqing Zhu , Bo Liu , Ming Ding , Dayong Ye , Wanlei Zhou , Philip S. Yu

With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such…

Multiagent Systems · Computer Science 2025-03-14 Miao Yu , Fanci Meng , Xinyun Zhou , Shilong Wang , Junyuan Mao , Linsey Pang , Tianlong Chen , Kun Wang , Xinfeng Li , Yongfeng Zhang , Bo An , Qingsong Wen

Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory systems transition from…

Artificial Intelligence · Computer Science 2026-05-20 Chingkwun Lam , Jiaxin Li , Lingfei Zhang , Kuo Zhao

Large Language Model (LLM) based agents are powerful yet fundamentally static after deployment, lacking the ability to autonomously expand capabilities, generate new tools, or evolve their reasoning. This work introduces a hierarchical…

Computation and Language · Computer Science 2026-01-21 Indrajit Kar , Sammy Zonunpuia , Zonunfeli Ralte

Role-playing enables large language models (LLMs) to engage users in immersive and personalized interactions, but it also introduces significant safety risks. Existing role-play fine-tuning techniques improve role adaptability but may…

Computation and Language · Computer Science 2025-05-28 Weixiang Zhao , Yulin Hu , Yang Deng , Jiahe Guo , Xingyu Sui , Xinyang Han , An Zhang , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise…

Cryptography and Security · Computer Science 2025-07-16 Ronny Ko , Jiseong Jeong , Shuyuan Zheng , Chuan Xiao , Tae-Wan Kim , Makoto Onizuka , Won-Yong Shin

In the age of AI-powered educational (AIED) innovation, evaluating the developmental consequences of novel designs before they are exposed to students has become both essential and challenging. Since such interventions may carry…

Computers and Society · Computer Science 2025-10-13 Jianxiao Jiang , Yu Zhang

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

Computation and Language · Computer Science 2026-04-16 Runnan Fang , Yuan Liang , Xiaobin Wang , Jialong Wu , Shuofei Qiao , Pengjun Xie , Fei Huang , Huajun Chen , Ningyu Zhang