English
Related papers

Related papers: Guardrails as Infrastructure: Policy-First Control…

200 papers

Reinforcement learning (RL) fine-tuning transforms large language models while creating a vulnerability we experimentally verify: Our experiment shows that malicious RL fine-tuning dismantles safety guardrails with remarkable efficiency,…

Machine Learning · Computer Science 2025-05-08 Wenjun Cao

Actuator faults heavily affect the performance and stability of control systems, an issue that is even more critical for systems required to operate autonomously under adverse environmental conditions, such as unmanned vehicles. To this…

Systems and Control · Electrical Eng. & Systems 2025-03-17 Daniele Masti , Davide Grande , Andrea Peruffo , Filippo Fabiani

Skin-friction drag induced by wall-bounded turbulent flows accounts for a substantial fraction of energy consumption across commercial aerospace, wind energy, and marine transport. Its active reduction is one of the highest-value targets in…

Fluid Dynamics · Physics 2026-05-15 Atharva Mahajan , Abhijeet Vishwasrao , Yuning Wang , Ricardo Vinuesa

The rapid development of autonomous web agents powered by Large Language Models (LLMs), while greatly elevating efficiency, exposes the frontier risk of taking unintended or harmful actions. This situation underscores an urgent need for…

Artificial Intelligence · Computer Science 2025-07-22 Boyuan Zheng , Zeyi Liao , Scott Salisbury , Zeyuan Liu , Michael Lin , Qinyuan Zheng , Zifan Wang , Xiang Deng , Dawn Song , Huan Sun , Yu Su

Imitation learning (IL) has shown great success in learning complex robot manipulation tasks. However, there remains a need for practical safety methods to justify widespread deployment. In particular, it is important to certify that a…

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

Computation and Language · Computer Science 2026-03-04 Aradhye Agarwal , Gurdit Siyan , Yash Pandya , Joykirat Singh , Akshay Nambi , Ahmed Awadallah

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Cryptography and Security · Computer Science 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

LLM-based agents are deployed in safety-critical applications, yet current guardrail systems fail to prevent violations of temporal safety policies, requirements that govern the ordering and sequencing of agent actions. For instance, agents…

Programming Languages · Computer Science 2026-01-01 Adharsh Kamath , Sishen Zhang , Calvin Xu , Shubham Ugare , Gagandeep Singh , Sasa Misailovic

As Large Language Models (LLMs) transition from research environments to production deployments, evaluating their performance against strict Service Level Objectives (SLOs) has become critical. However, current evaluation methodologies…

Artificial Intelligence · Computer Science 2026-05-27 Ashok Chandrasekar , Jason Kramberger

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Cryptography and Security · Computer Science 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language…

Cryptography and Security · Computer Science 2026-01-27 Narek Maloyan , Dmitry Namiot

Offline reinforcement learning (RL) provides a compelling paradigm for training autonomous systems without the risks of online exploration, particularly in safety-critical domains. However, jointly achieving strong safety and performance…

Machine Learning · Computer Science 2026-02-10 Manan Tayal , Mumuksh Tayal

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a…

Computation and Language · Computer Science 2026-02-09 Jianfeng Si , Lin Sun , Weihong Lin , Xiangzheng Zhang

Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a…

Cryptography and Security · Computer Science 2025-12-18 S M Asif Hossain , Ruksat Khan Shayoni , Mohd Ruhul Ameen , Akif Islam , M. F. Mridha , Jungpil Shin

Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly susceptible to the error in cumulative cost estimation since…

Machine Learning · Computer Science 2024-04-16 Zifan Wu , Bo Tang , Qian Lin , Chao Yu , Shangqin Mao , Qianlong Xie , Xingxing Wang , Dong Wang

GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…

Artificial Intelligence · Computer Science 2026-05-15 Drewry H. Morris , Luis Valles , Reza Hosseini Ghomi

Software-defined networking (SDN) has become a fundamental technology for data centers and 5G networks. In an SDN network, routing and traffic management decisions are made by a centralized controller and communicated to switches via a…

Networking and Internet Architecture · Computer Science 2020-10-23 Michael Sjoholmsierchio , Britta Hale , Daniel Lukaszewski , Geoffrey G. Xie

Programmable Logic Controllers (PLCs) are the core control devices in Industrial Control Systems (ICSs), which control and monitor the underlying physical plants such as power grids. PLCs were initially designed to work in a trusted…

Cryptography and Security · Computer Science 2023-01-02 Rongkuan Ma , Qiang Wei , Jingyi Wang , Shunkai Zhu , Shouling Ji , Peng Cheng , Yan Jia , Qingxian Wang

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…

Machine Learning · Computer Science 2021-02-26 Miguel Calvo-Fullana , Luiz F. O. Chamon , Santiago Paternain

We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks…

Computation and Language · Computer Science 2026-01-07 Jakub Hoscilowicz