English
Related papers

Related papers: Why Agents Compromise Safety Under Pressure

200 papers

The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…

Artificial Intelligence · Computer Science 2026-03-02 Sheng Cao , Zhao Chang , Chang Li , Hannan Li , Liyao Fu , Ji Tang

As autonomous agents become more prevalent, understanding their collective behaviour in strategic interactions is crucial. This study investigates the emergent cooperative tendencies of systems of Large Language Model (LLM) agents in a…

Multiagent Systems · Computer Science 2025-01-28 Richard Willis , Yali Du , Joel Z Leibo , Michael Luck

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

Agentic systems powered by large language models (LLMs) are becoming progressively more complex and capable. Their increasing agency and expanding deployment settings attract growing attention to effective governance policies, monitoring,…

Computers and Society · Computer Science 2025-08-06 Garry A. Gabison , R. Patrick Xian

Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…

Networking and Internet Architecture · Computer Science 2026-05-05 Purna Sai Garigipati , Onur Ayan , Kishor Chandra Joshi , Xueli An

Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure…

Artificial Intelligence · Computer Science 2019-10-30 Fushan Li , Michael Bowling

Agent-based modeling and simulation has evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors and interactions among diverse agents. Integrating large language models into agent-based modeling…

Artificial Intelligence · Computer Science 2023-12-20 Chen Gao , Xiaochong Lan , Nian Li , Yuan Yuan , Jingtao Ding , Zhilun Zhou , Fengli Xu , Yong Li

Clinical dialogue represents a complex duality requiring both the empathetic fluency of natural conversation and the rigorous precision of evidence-based medicine. While Large Language Models possess unprecedented linguistic capabilities,…

Other Quantitative Biology · Quantitative Biology 2025-12-02 Xiaoquan Zhi , Hongke Zhao , Likang Wu , Chuang Zhao , Hengshu Zhu

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Computation and Language · Computer Science 2025-04-02 Samuel M. Taylor , Benjamin K. Bergen

As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…

Artificial Intelligence · Computer Science 2025-07-04 Joseph Boland

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…

Cryptography and Security · Computer Science 2026-05-12 Ziwen Cai , Yihe Zhang , Xiali Hei

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding their cooperation and social mechanisms is becoming increasingly important. In particular, how LLMs balance self-interest and collective…

Artificial Intelligence · Computer Science 2025-07-25 David Guzman Piedrahita , Yongjin Yang , Mrinmaya Sachan , Giorgia Ramponi , Bernhard Schölkopf , Zhijing Jin

The enhanced capabilities of LLM-based agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM alignment, agents typically also inherit the flaw of "over-refusal", which is…

Computation and Language · Computer Science 2026-02-05 Xinyue Wang , Yuanhe Zhang , Zhengshuo Gong , Haoran Gao , Fanyu Meng , Zhenhong Zhou , Li Sun , Yang Liu , Sen Su

In recent years, agents have become capable of communicating seamlessly via natural language and navigating in environments that involve cooperation and competition, a fact that can introduce social dilemmas. Due to the interleaving of…

Artificial Intelligence · Computer Science 2025-01-28 Maayan Orner , Oleg Maksimov , Akiva Kleinerman , Charles Ortiz , Sarit Kraus

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…

Software Engineering · Computer Science 2026-01-14 Aarya Doshi , Yining Hong , Congying Xu , Eunsuk Kang , Alexandros Kapravelos , Christian Kästner

Eliciting reasoning has emerged as a powerful technique for improving the performance of large language models (LLMs) on complex tasks by inducing thinking. However, their effectiveness in realistic user-engaged agent scenarios remains…

Computation and Language · Computer Science 2026-02-10 Jiatong Li , Changdae Oh , Hyeong Kyu Choi , Jindong Wang , Sharon Li

Conflicts between user preferences and automated system behavior already shape the experience of automated mobility. For example, a passenger may prefer assertive driving, yet the vehicle slows down early to follow a conservative policy or…

Human-Computer Interaction · Computer Science 2026-03-03 Pascal Jansen

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…

Computation and Language · Computer Science 2019-09-11 Jason Lee , Kyunghyun Cho , Douwe Kiela

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and…

‹ Prev 1 4 5 6 7 8 10 Next ›