中文
相关论文

相关论文: AgentBreeder: Mitigating the AI Safety Risks of Mu…

200 篇论文

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…

计算机与社会 · 计算机科学 2026-05-19 Miles Q. Li , Benjamin C. M. Fung , Boyang Li , Heba Ismail , Farkhund Iqbal

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

密码学与安全 · 计算机科学 2026-04-09 Hongyi Lu , Nian Liu , Shuai Wang , Fengwei Zhang

Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs…

Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to…

多智能体系统 · 计算机科学 2025-07-11 Sinem Erisken , Timothy Gothard , Martin Leitgab , Ram Potham

Exploratoration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding accelerating skill and knowledge acquisition. In developmental robotics, this approach…

机器人学 · 计算机科学 2024-01-03 Batuhan Celik , Alper Ahmetoglu , Emre Ugur , Erhan Oztop

Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…

多智能体系统 · 计算机科学 2026-04-28 Juan A. Wibowo , George C. Polyzos

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…

人工智能 · 计算机科学 2025-10-01 Ruolin Chen , Yinqian Sun , Jihang Wang , Mingyang Lv , Qian Zhang , Yi Zeng

Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks,…

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

密码学与安全 · 计算机科学 2026-05-12 Xixun Lin , Yang Liu , Yancheng Chen , Yongxuan Wu , Yucheng Ning , Yilong Liu , Nan Sun , Shun Zhang , Bin Chong , Chuan Zhou , Yanan Cao

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

人工智能 · 计算机科学 2025-04-02 Seyoung Song

Multi-agent large language models (MA-LLMs) are a rapidly growing research area that leverages multiple interacting language agents to tackle complex tasks, outperforming single-agent large language models. This literature review…

多智能体系统 · 计算机科学 2025-06-03 Arne Tillmann

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current…

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

人工智能 · 计算机科学 2026-04-07 Bowen Wei , Yunbei Zhang , Jinhao Pan , Kai Mei , Xiao Wang , Jihun Hamm , Ziwei Zhu , Yingqiang Ge

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

密码学与安全 · 计算机科学 2024-07-31 Boyang Zhang , Yicong Tan , Yun Shen , Ahmed Salem , Michael Backes , Savvas Zannettou , Yang Zhang

Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs).…

密码学与安全 · 计算机科学 2026-03-24 Xiaolei Zhang , Lu Zhou , Xiaogang Xu , Jiafei Wu , Tianyu Du , Heqing Huang , Hao Peng , Zhe Liu

As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework…

多智能体系统 · 计算机科学 2026-05-12 Yang Shen , Zhenyi Yi , Ziyi Zhao , Lijun Sun , Dongyang Li , Chin-Teng Lin , Yuhui Shi

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinement framework designed…

Autonomous agents driven by Large Language Models (LLMs) offer enormous potential for automation. Early proof of this technology can be found in various demonstrations of agents solving complex tasks, interacting with external systems to…

A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable nuanced protocols that account for unstructured private data,…