English
Related papers

Related papers: ChainCaps: Composition-Safe Tool-Using Agents via …

200 papers

LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal…

Cryptography and Security · Computer Science 2026-04-01 Haoyu Wang , Zibo Xiao , Yedi Zhang , Christopher M. Poskitt , Jun Sun

We propose a new formal criterion for evaluating secure compilation schemes for unsafe languages, expressing end-to-end security guarantees for software components that may become compromised after encountering undefined behavior---for…

Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…

Logic in Computer Science · Computer Science 2026-03-24 Melwin Xavier , Vaisakh M A , Melveena Jolly , Midhun Xavier

LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on this substrate for safety-critical \emph{Prognostics and Health Management (PHM)} is…

Artificial Intelligence · Computer Science 2026-05-12 Tianjun Feng , Yunfeng Chen , Chun-Yi Tsai , Yihan Sun , Ayan Das , Kaoutar El Maghraoui , Shuxin Lin , Dhaval Patel

We study how organizations should select among competing AI models when user utility, deployment costs, and compliance requirements jointly matter. Widely used capability leaderboards do not translate directly into deployment decisions,…

Machine Learning · Computer Science 2025-12-30 Vassilis Digalakis , Ramayya Krishnan , Gonzalo Martin Fernandez , Agni Orfanoudaki

Collaborative driving systems leverage vehicle-to-everything (V2X) communication across multiple agents to enhance driving safety and efficiency. Traditional V2X systems take raw sensor data, neural features, or perception results as…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Xiangbo Gao , Tzu-Hsiang Lin , Ruojing Song , Yuheng Wu , Kuan-Ru Huang , Zicheng Jin , Fangzhou Lin , Shinan Liu , Zhengzhong Tu

Every Python function deployed as an LLM tool must today exist in two forms: an HTTP endpoint for human-facing clients and CI pipelines, and an MCP tool registration for agent runtimes such as Claude and Cursor. These representations share…

Artificial Intelligence · Computer Science 2026-05-22 Edwin Jose

The increasing complexity of user demands necessitates automation frameworks that can reliably translate open-ended instructions into robust, multi-step workflows. Current monolithic agent architectures often struggle with the challenges of…

Computation and Language · Computer Science 2026-03-23 Eslam Reda , Maged Yasser , Sara El-Metwally

Production deployment of AI coding agents requires fast, reproducible evaluation signals. Existing industrial practices trade off speed and fidelity: online A/B testing takes weeks and risks user experience, shadow deployment yields signals…

Software Engineering · Computer Science 2026-05-12 Smriti Jha , Matteo Paltenghi , Chandra Maddila , Vijayaraghavan Murali , Shubham Ugare , Satish Chandra

To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthropic, 2024) has recently been released and subsequently…

Cryptography and Security · Computer Science 2025-04-14 Brandon Radosevich , John Halloran

To standardize interactions between LLM-based agents and their environments, the Model Context Protocol (MCP) was proposed and has since been widely adopted. However, integrating external tools expands the attack surface, exposing agents to…

Cryptography and Security · Computer Science 2026-01-13 Ruiqi Li , Zhiqiang Wang , Yunhao Yao , Xiang-Yang Li

Tool-calling LLM agents can read private data, invoke external services, and trigger real-world actions, creating a security problem at the point of tool execution. We identify a denial-feedback leakage pattern, which we term causality…

Cryptography and Security · Computer Science 2026-04-07 Mohammad Hossein Chinaei

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

Cryptography and Security · Computer Science 2025-12-30 Toqeer Ali Syed , Mishal Ateeq Almutairi , Mahmoud Abdel Moaty

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…

Cryptography and Security · Computer Science 2026-05-18 Zheng Yan , Jingxiang Weng , Charles Chen , Dengyun Peng , Ethan Qin , Jiannan Guan , Jinhao Liu , Qiming Yu , Yixin Yuan , Fanqing Meng , Carl Che , Mengkang Hu

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

Cryptography and Security · Computer Science 2026-03-16 Zonghao Ying , Xiao Yang , Siyang Wu , Yumeng Song , Yang Qu , Hainan Li , Tianlin Li , Jiakai Wang , Aishan Liu , Xianglong Liu

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

The latency reduction between the discovery of vulnerabilities, the build-up and dissemination of cyber-attacks has put significant pressure on cybersecurity professionals. For that, security researchers have increasingly resorted to…

Cryptography and Security · Computer Science 2022-10-11 Sébastien Gillard , Dimitri Percia David , Alain Mermoud , Thomas Maillart

AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the action executes. Current…

Cryptography and Security · Computer Science 2026-03-24 Uchi Uchibeke

Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting inside enterprise systems. Yet the tool layer on which this execution depends is still…

Software Engineering · Computer Science 2026-05-28 Swanand Rao

Agent communication remains a foundational problem in multi-agent systems: protocols such as FIPA-ACL guarantee semantic richness but are intractable for constrained environments, while lightweight IoT protocols achieve efficiency at the…

Multiagent Systems · Computer Science 2026-05-26 Arnab Mallick , Indraveni Chebolu
‹ Prev 1 4 5 6 7 8 10 Next ›