English
Related papers

Related papers: Beyond Static Sandboxing: Learned Capability Gover…

200 papers

Despite remarkable achievements in artificial intelligence, the deployability of learning-enabled systems in high-stakes real-world environments still faces persistent challenges. For example, in safety-critical domains like autonomous…

Artificial Intelligence · Computer Science 2023-12-19 Minjae Cho , Chuangchuang Sun

An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its coverage of experience/data is broad enough,…

Artificial Intelligence · Computer Science 2024-11-27 Tom Schaul

AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization,…

Cryptography and Security · Computer Science 2026-02-25 Genliang Zhu , Chu Wang , Ziyuan Wang , Zhida Li , Qiang Li

A fundamental aspect of behaviour is the ability to encode salient features of experience in memory and use these memories, in combination with current sensory information, to predict the best action for each situation such that long-term…

Neural and Evolutionary Computing · Computer Science 2021-06-25 Stephen Kelly , Tatiana Voegerl , Wolfgang Banzhaf , Cedric Gondro

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Current AI agent frameworks have made remarkable progress in automating individual tasks, yet all existing systems serve a single user. Human productivity rests on the social and organizational relationships through which people coordinate,…

Artificial Intelligence · Computer Science 2026-04-22 Zhiqin Yang , Zhenyuan Zhang , Xianzhang Jia , Jun Song , Wei Xue , Yonggang Zhang , Yike Guo

We study a Stackelberg game between one attacker and one defender in a configurable environment. The defender picks a specific environment configuration. The attacker observes the configuration and attacks via Reinforcement Learning (RL…

Neural and Evolutionary Computing · Computer Science 2023-04-11 Diksha Goel , Aneta Neumann , Frank Neumann , Hung Nguyen , Mingyu Guo

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for…

Computation and Language · Computer Science 2026-05-13 Xiaoyuan Li , Moxin Li , Keqin Bao , Yubo Ma , Wenjie Wang , Dayiheng Liu , Fuli Feng

In the domain of combat simulations in support of wargaming, the development of intelligent agents has predominantly been characterized by rule-based, scripted methodologies with deep reinforcement learning (RL) approaches only recently…

Machine Learning · Computer Science 2025-12-02 Scotty Black , Christian Darken

The creation of effective governance mechanisms for AI agents requires a deeper understanding of their core properties and how these properties relate to questions surrounding the deployment and operation of agents in the world. This paper…

Computers and Society · Computer Science 2025-05-01 Atoosa Kasirzadeh , Iason Gabriel

This paper develops a control-theoretic framework for analyzing agentic systems embedded within feedback control loops, where an AI agent may adapt controller parameters, select among control strategies, invoke external tools, reconfigure…

Systems and Control · Electrical Eng. & Systems 2026-03-26 Ali Eslami , Jiangbo Yu

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…

Cybersecurity is a relentless arms race, with AI driven offensive systems evolving faster than traditional defenses can adapt. Research and tooling remain fragmented across isolated defensive functions, creating blind spots that adversaries…

Computation and Language · Computer Science 2025-10-03 Mudita Khurana , Raunak Jain

The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents. Recent work on generating adversarial attacks have shown that it is…

Machine Learning · Computer Science 2018-07-18 Aaron J. Havens , Zhanhong Jiang , Soumik Sarkar

A significant challenge for autonomous cyber defence is ensuring a defensive agent's ability to generalise across diverse network topologies and configurations. This capability is necessary for agents to remain effective when deployed in…

Machine Learning · Computer Science 2025-01-27 Isaac Symes Thompson , Alberto Caron , Chris Hicks , Vasilios Mavroudis

Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…

Artificial Intelligence · Computer Science 2026-05-12 Genrui Zhang , Erle Zhu , Jinfeng Zhou , Caiyan Jia , Hongning Wang

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…

Hardware Architecture · Computer Science 2025-11-13 Eren Kurshan , Yuan Xie , Paul Franzon

The deployment of autonomous AI agents in derivatives markets has widened a practical gap between static model calibration and realized hedging outcomes. We introduce two reinforcement learning frameworks, a novel Replication Learning of…

Artificial Intelligence · Computer Science 2026-03-10 Minxuan Hu , Ziheng Chen , Jiayu Yi , Wenxi Sun

Federated Learning (FL) offers a paradigm for privacy-preserving collaborative AI, but its decentralized nature creates significant vulnerabilities to model poisoning attacks. While numerous static defenses exist, their effectiveness is…

Machine Learning · Computer Science 2025-07-30 Md Rafid Haque , Abu Raihan Mostofa Kamal , Md. Azam Hossain

Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…

Artificial Intelligence · Computer Science 2026-05-08 Bowen Ye , Rang Li , Qibin Yang , Yuanxin Liu , Linli Yao , Hanglong Lv , Zhihui Xie , Chenxin An , Lei Li , Lingpeng Kong , Qi Liu , Zhifang Sui , Tong Yang