English
Related papers

Related papers: On Safety Risks in Experience-Driven Self-Evolving…

200 papers

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as…

Artificial Intelligence · Computer Science 2024-11-15 Yuyou Gan , Yong Yang , Zhe Ma , Ping He , Rui Zeng , Yiming Wang , Qingming Li , Chunyi Zhou , Songze Li , Ting Wang , Yunjun Gao , Yingcai Wu , Shouling Ji

Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental…

Computation and Language · Computer Science 2021-02-02 Gautier Dagan , Dieuwke Hupkes , Elia Bruni

Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…

Artificial Intelligence · Computer Science 2025-07-01 Hang Su , Jun Luo , Chang Liu , Xiao Yang , Yichi Zhang , Yinpeng Dong , Jun Zhu

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

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

Artificial Intelligence · Computer Science 2021-04-20 Aquib Mustafa , Majid Mazouchi , Subramanya Nageshrao , Hamidreza Modares

AI agents are increasingly deployed in multi-task settings, where the task to perform is specified at test time, and the agent must generalize to unseen tasks. A major concern in such settings is safety: often, an agent must not only…

Machine Learning · Computer Science 2026-05-11 Yonatan Slutzky , Yotam Alexander , Tomer Slor , Yoav Nagel , Nadav Cohen

Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that…

Artificial Intelligence · Computer Science 2026-04-21 Gonzalo Gonzalez-Pumariega , Saaket Agashe , Jiachen Yang , Ang Li , Xin Eric Wang

Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after…

Artificial Intelligence · Computer Science 2025-09-03 Jinyuan Fang , Yanwen Peng , Xi Zhang , Yingxu Wang , Xinhao Yi , Guibin Zhang , Yi Xu , Bin Wu , Siwei Liu , Zihao Li , Zhaochun Ren , Nikos Aletras , Xi Wang , Han Zhou , Zaiqiao Meng

Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for…

Machine Learning · Computer Science 2025-08-20 Yasir Zubayr Barlas , Kizito Salako

Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and…

Machine Learning · Statistics 2017-05-29 Agostino Capponi , Reza Ghanadan , Matt Stern

In this work, we describe a self-replication-based mechanism for designing agents of increasing complexity. We demonstrate the validity of this approach by solving simple, standard evolutionary computation problems in simulation. In the…

Neural and Evolutionary Computing · Computer Science 2018-07-20 Thommen George Karimpanal

Agents of general intelligence deployed in real-world scenarios must adapt to ever-changing environmental conditions. While such adaptive agents may leverage engineered knowledge, they will require the capacity to construct and evaluate…

Artificial Intelligence · Computer Science 2016-06-20 Craig Sherstan , Adam White , Marlos C. Machado , Patrick M. Pilarski

Reinforcement Learning (RL) agents have great successes in solving tasks with large observation and action spaces from limited feedback. Still, training the agents is data-intensive and there are no guarantees that the learned behavior is…

Artificial Intelligence · Computer Science 2021-10-20 Helge Spieker

Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents. Control Barrier Functions (CBFs) are showing promise for safety assurance but current methods make strong assumptions about…

Robotics · Computer Science 2023-10-05 Luigi Berducci , Shuo Yang , Rahul Mangharam , Radu Grosu

Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent…

Machine Learning · Computer Science 2020-02-12 Bowen Baker , Ingmar Kanitscheider , Todor Markov , Yi Wu , Glenn Powell , Bob McGrew , Igor Mordatch

Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent…

Computation and Language · Computer Science 2026-05-22 Weiwei Xie , Shaoxiong Guo , Fan Zhang , Tian Xia , Xue Yang , Lizhuang Ma , Junchi Yan , Qibing Ren

Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These…

Information Retrieval · Computer Science 2025-10-07 Kirandeep Kaur , Preetam Prabhu Srikar Dammu , Hideo Joho , Chirag Shah

Host-acting agents promise a convenient interaction model in which users specify goals and the system determines how to realize them. We argue that this convenience introduces a distinct security problem: semantic under-specification in…

Cryptography and Security · Computer Science 2026-03-24 Di Lu , Yongzhi Liao , Xutong Mu , Lele Zheng , Ke Cheng , Xuewen Dong , Yulong Shen , Jianfeng Ma

Data for training learning-enabled self-driving cars in the physical world are typically collected in a safe, normal environment. Such data distribution often engenders a strong bias towards safe driving, making self-driving cars unprepared…

In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or avoiding overly technical wording, yet such interaction experience…

Artificial Intelligence · Computer Science 2026-03-06 Yutao Yang , Junsong Li , Qianjun Pan , Bihao Zhan , Yuxuan Cai , Lin Du , Jie Zhou , Kai Chen , Qin Chen , Xin Li , Bo Zhang , Liang He