English
Related papers

Related papers: How Brittle is Agent Safety? Rethinking Agent Risk…

200 papers

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…

Artificial Intelligence · Computer Science 2025-05-20 Junting Lu , Zhiyang Zhang , Fangkai Yang , Jue Zhang , Lu Wang , Chao Du , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Qi Zhang

As the reasoning capabilities of Large Language Models (LLMs) continue to advance, LLM-based agent systems offer advantages in flexibility and interpretability over traditional systems, garnering increasing attention. However, despite the…

Artificial Intelligence · Computer Science 2025-08-05 Zexin Wang , Jingjing Li , Quan Zhou , Haotian Si , Yuanhao Liu , Jianhui Li , Gaogang Xie , Fei Sun , Dan Pei , Changhua Pei

As companies enter the race for agentic AI adoption, fears surface around agentic autonomy and its subsequent risks. These fears compound as companies scale their agentic AI adoption with low-code applications, without a comparable scaling…

Human-Computer Interaction · Computer Science 2026-04-17 Yomna Elsayed , Cecily Jones

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms…

Computation and Language · Computer Science 2026-05-29 Aditya Nawal , Manit Baser , Mohan Gurusamy

Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information…

Cryptography and Security · Computer Science 2026-03-04 Jian Cui , Zichuan Li , Luyi Xing , Xiaojing Liao

Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility…

Artificial Intelligence · Computer Science 2024-02-16 Paulo Garcia

One of the unresolved challenges for autonomous vehicles is safe navigation among occluded pedestrians and vehicles. Previous approaches included generating phantom vehicles and assessing their risk, but they often made the ego vehicle…

Robotics · Computer Science 2023-10-31 Hyunwoo Park , Jongseo Choi , Hyuntai Chin , Sang-Hyun Lee , Doosan Baek

The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…

Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process…

Cryptography and Security · Computer Science 2024-12-24 Feiran Jia , Tong Wu , Xin Qin , Anna Squicciarini

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

Machine Learning · Computer Science 2025-10-31 David Schmotz , Sahar Abdelnabi , Maksym Andriushchenko

The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex GUIs. However, the transition of these agents into…

Computation and Language · Computer Science 2026-04-28 Zheng Wu , Yi Hua , Zhaoyuan Huang , Chenhao Xue , Yijie Lu , Pengzhou Cheng , Zongru Wu , Lingzhong Dong , Gongshen Liu , Xinghao Jiang , Zhuosheng Zhang

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Cryptography and Security · Computer Science 2025-02-17 Jizhou Chen , Samuel Lee Cong

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

Cryptography and Security · Computer Science 2026-01-21 Roy Betser , Shamik Bose , Amit Giloni , Chiara Picardi , Sindhu Padakandla , Roman Vainshtein

Agentic systems have transformed how Large Language Models (LLMs) can be leveraged to create autonomous systems with goal-directed behaviors, consisting of multi-step planning and the ability to interact with different environments. These…

Artificial Intelligence · Computer Science 2026-01-27 Judy Zhu , Dhari Gandhi , Himanshu Joshi , Ahmad Rezaie Mianroodi , Sedef Akinli Kocak , Dhanesh Ramachandran

In multiagent systems (MASs), agents' observation upon system behaviours may improve the overall team performance, but may also leak sensitive information to an observer. A quantified observability analysis can thus be useful to assist…

Artificial Intelligence · Computer Science 2023-10-05 Chunyan Mu , Jun Pang

Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing…

Artificial Intelligence · Computer Science 2026-03-18 Muyu He , Anand Kumar , Tsach Mackey , Meghana Rajeev , James Zou , Nazneen Rajani

The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM…

Multiagent Systems · Computer Science 2025-02-05 Jinwei Hu , Yi Dong , Shuang Ao , Zhuoyun Li , Boxuan Wang , Lokesh Singh , Guangliang Cheng , Sarvapali D. Ramchurn , Xiaowei Huang

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Machine Learning · Computer Science 2025-12-03 Tsimur Hadeliya , Mohammad Ali Jauhar , Nidhi Sakpal , Diogo Cruz

Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a…

Operating Systems · Computer Science 2025-10-21 Yusheng Zheng , Yanpeng Hu , Tong Yu , Andi Quinn

With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…

Artificial Intelligence · Computer Science 2026-04-07 Prince Zizhuang Wang , Shuli Jiang