中文
相关论文

相关论文: When Autonomy Goes Rogue: Preparing for Risks of M…

200 篇论文

Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication…

多智能体系统 · 计算机科学 2025-10-22 Michael J. Wooldridge , Attila Bagoly , Jonathan J. Ward , Emanuele La Malfa , Gabriel Paludo Licks

LLM agents in markets present algorithmic collusion risks. While prior work shows LLM agents reach supracompetitive prices through tacit coordination, existing research focuses on hand-crafted prompts. The emerging paradigm of prompt…

人工智能 · 计算机科学 2026-04-21 Yingtao Tian

As AI systems evolve into distributed ecosystems with autonomous execution, asynchronous reasoning, and multi-agent coordination, the absence of scalable, decoupled governance poses a structural risk. Existing oversight mechanisms are…

机器学习 · 计算机科学 2025-08-28 Suyash Gaurav , Jukka Heikkonen , Jatin Chaudhary

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

计算机与社会 · 计算机科学 2026-02-24 Nelu D. Radpour

A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…

人工智能 · 计算机科学 2026-05-18 Aleksandr Bowkis , Marie Davidsen Buhl , Jacob Pfau , Geoffrey Irving

We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamination, the lack of reliable ground truth for novel research…

计算机与社会 · 计算机科学 2026-04-07 Marcin Abram

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

密码学与安全 · 计算机科学 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

软件工程 · 计算机科学 2025-12-29 Brian Bowers , Smita Khapre , Jugal Kalita

The rise of large language model (LLM)-based multi-agent systems (MAS) introduces new security and reliability challenges. While these systems show great promise in decomposing and coordinating complex tasks, they also face multi-faceted…

人工智能 · 计算机科学 2025-06-02 Xu He , Di Wu , Yan Zhai , Kun Sun

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,…

In this paper a decentralized control algorithm for systems composed of $N$ dynamically decoupled agents, coupled by feasibility constraints, is presented. The control problem is divided into $N$ optimal control sub-problems and a…

多智能体系统 · 计算机科学 2017-02-28 Ugo Rosolia , Francesco Braghin , Andrew G. Alleyne , Stijn De Bruyne , Edoardo Sabbioni

This report examines what I see as the core argument for concern about existential risk from misaligned artificial intelligence. I proceed in two stages. First, I lay out a backdrop picture that informs such concern. On this picture,…

计算机与社会 · 计算机科学 2024-08-14 Joseph Carlsmith

AI scientists powered by large language models have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these…

AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks…

人工智能 · 计算机科学 2025-02-24 Peter Cihon , Merlin Stein , Gagan Bansal , Sam Manning , Kevin Xu

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to…

多智能体系统 · 计算机科学 2021-04-26 Alex Tong Lin , Mark J. Debord , Katia Estabridis , Gary Hewer , Guido Montufar , Stanley Osher

From denial-of-service attacks to spreading of ransomware or other malware across an organization's network, it is possible that manually operated defenses are not able to respond in real time at the scale required, and when a breach is…

密码学与安全 · 计算机科学 2022-01-28 Alexandre K. Ligo , Alexander Kott , Igor Linkov

The expanding application of Artificial Intelligence (AI) in scientific fields presents unprecedented opportunities for discovery and innovation. However, this growth is not without risks. AI models in science, if misused, can amplify risks…

We consider the setting where a team of robots is tasked with tracking multiple targets with the following property: approaching the targets enables more accurate target position estimation, but also increases the risk of sensor failures.…

机器人学 · 计算机科学 2022-10-18 Jiazhen Liu , Lifeng Zhou , Ragesh Ramachandran , Gaurav S. Sukhatme , Vijay Kumar

Significant digitalization of financial services in a short period of time has led to an urgent demand to have autonomous, transparent and real-time credit risk decision making systems. The traditional machine learning models are effective…

人工智能 · 计算机科学 2026-01-06 Chandra Sekhar Kubam

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…

密码学与安全 · 计算机科学 2025-07-30 Gauri Sharma , Vidhi Kulkarni , Miles King , Ken Huang