English
Related papers

Related papers: The Authorization-Execution Gap Is a Major Safety …

200 papers

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…

Artificial Intelligence · Computer Science 2026-05-13 Strick Sheng , Ziyue Wang , Liyi Zhou

Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is…

Cryptography and Security · Computer Science 2026-05-12 Rohan Sequeira , Stavros Damianakis , Umar Iqbal , Konstantinos Psounis

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

Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language…

Software Engineering · Computer Science 2026-03-24 Shasha Yu , Fiona Carroll , Barry L. Bentley

Agentic systems that chain reasoning, tool use, and synthesis into multi-step workflows are entering production, yet prevailing evaluation practices like end-to-end outcome checks and ad-hoc trace inspection systematically mask the…

Software Engineering · Computer Science 2026-04-28 Dongxin Guo , Jikun Wu , Siu Ming Yiu

We introduce the Agent GPA (Goal-Plan-Action) framework, driven by the fundamental insight that critical agent failures emerge at the intersections of setting goals, devising plans, and executing actions. We operationalize the framework…

Artificial Intelligence · Computer Science 2026-03-31 Allison Sihan Jia , Daniel Huang , Nikhil Vytla , Seung Won Wilson Yoo , Nirvika Choudhury , Shayak Sen , John C. Mitchell , Anupam Datta

An intelligent agent may in general pursue multiple procedural goals simultaneously, which may lead to arise some conflicts (incompatibilities) among them. In this paper, we focus on the incompatibilities that emerge due to resources…

Artificial Intelligence · Computer Science 2020-09-15 Mariela Morveli-Espinoza , Ayslan Possebom , Cesar Augusto Tacla

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors…

Cryptography and Security · Computer Science 2026-05-25 Tanzim Ahad , Ismail Hossain , Md Jahangir Alam , Sai Puppala , Syed Bahauddin Alam , Sajedul Talukder

As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents…

Multiagent Systems · Computer Science 2025-04-08 Sagar Tamang , Dibya Jyoti Bora

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Artificial Intelligence · Computer Science 2026-05-20 Qiqi Liu , Thorsten Holz , Shilin Ye , Runhan Song

Multi-agent systems have extended the capability of agentic AI. Instead of single inference passes, multiple agents perform collective reasoning to derive high quality answers. However, existing multi-agent orchestration relies on static…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-24 Chaoyi Ruan , Yiliang Wang , Ziji Shi , Jialin Li

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…

Computers and Society · Computer Science 2025-03-11 Krti Tallam

We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, overwrote a system registry, overrode a prior negative decision from an oversight agent, and…

Cryptography and Security · Computer Science 2026-05-04 Diego F. Cuadros , Abdoul-Aziz Maiga

Artificial Intelligence (AI) agents capable of autonomous learning and independent decision-making hold great promise for addressing complex challenges across various critical infrastructure domains, including transportation, energy…

Multiagent Systems · Computer Science 2025-07-02 Hepeng Li , Yuhong Liu , Jun Yan , Jie Gao , Xiaoou Yang

While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…

Artificial Intelligence · Computer Science 2025-12-12 Dani Roytburg , Beck Miller

Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second,…

With the growing adoption of retrieval-augmented generation (RAG) systems, various attack methods have been proposed to degrade their performance. However, most existing approaches rely on unrealistic assumptions in which external attackers…

Cryptography and Security · Computer Science 2025-10-31 Chanwoo Choi , Jinsoo Kim , Sukmin Cho , Soyeong Jeong , Buru Chang

During the execution of Multi-Agent Path Finding (MAPF) plans in real-life applications, the MAPF assumption that the fleet's movement is perfectly synchronized does not apply. Since one or more of the agents may become delayed due to…

Multiagent Systems · Computer Science 2026-04-29 David Zahrádka , David Woller , Denisa Mužíková , Miroslav Kulich , Libor Přeučil
‹ Prev 1 3 4 5 6 7 10 Next ›