English
Related papers

Related papers: Why Agents Compromise Safety Under Pressure

200 papers

As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…

Artificial Intelligence · Computer Science 2026-03-31 Mia Hopman , Jannes Elstner , Maria Avramidou , Amritanshu Prasad , David Lindner

Large Language Models (LLMs) are increasingly used to generate user-tailored summaries, adapting outputs to specific stakeholders. In legal contexts, this raises important questions about motivated reasoning -- how models strategically…

Computation and Language · Computer Science 2025-10-10 Eunjung Cho , Alexander Hoyle , Yoan Hermstrüwer

Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these…

Real-world decision-making systems operate in environments where state transitions depend not only on the agent's actions, but also on \textbf{exogenous factors outside its control}--competing agents, environmental disturbances, or…

Machine Learning · Computer Science 2026-04-20 Sourav Ganguly , Kartik Pandit , Arnob Ghosh

AI systems are increasingly deployed in high-stakes contexts (medical diagnosis, legal research, financial analysis) under the assumption they can be governed by norms. This paper demonstrates that the assumption is formally invalid for…

Artificial Intelligence · Computer Science 2026-03-03 Radha Sarma

The rapid growth of large language models has spurred significant interest in model compression as a means to enhance their accessibility and practicality. While extensive research has explored model compression through the lens of safety,…

Computation and Language · Computer Science 2025-04-08 Vishnu Kabir Chhabra , Mohammad Mahdi Khalili

There is increasing focus on adapting predictive models into agent-like systems, most notably AI assistants based on language models. We outline two structural reasons for why these models can fail when turned into agents. First, we discuss…

Artificial Intelligence · Computer Science 2024-02-09 Raymond Douglas , Jacek Karwowski , Chan Bae , Andis Draguns , Victoria Krakovna

Can emergent language models faithfully model the intelligence of decision-making agents? Though modern language models exhibit already some reasoning ability, and theoretically can potentially express any probable distribution over tokens,…

Machine Learning · Computer Science 2024-06-27 Wenhao Lu , Xufeng Zhao , Josua Spisak , Jae Hee Lee , Stefan Wermter

Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is vital for users' trust calibration, but explainable MAS face…

Artificial Intelligence · Computer Science 2025-10-30 Bálint Gyevnár , Christopher G. Lucas , Stefano V. Albrecht , Shay B. Cohen

The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical,…

Multiagent Systems · Computer Science 2025-10-07 Shengxiang Xu , Jiayi Zhang , Shimin Di , Yuyu Luo , Liang Yao , Hanmo Liu , Jia Zhu , Fan Liu , Min-Ling Zhang

Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter,…

Multiagent Systems · Computer Science 2025-10-17 Michael Rizvi-Martel , Satwik Bhattamishra , Neil Rathi , Guillaume Rabusseau , Michael Hahn

The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic,…

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

Multi-agent systems driven by large language models (LLMs) have shown promising abilities for solving complex tasks in a collaborative manner. This work considers a fundamental problem in multi-agent collaboration: consensus seeking. When…

Computation and Language · Computer Science 2025-01-22 Huaben Chen , Wenkang Ji , Lufeng Xu , Shiyu Zhao

Large Language Models (LLMs) have become foundational to modern AI agent systems, enabling autonomous agents to reason and plan. In most existing systems, inter-agent communication relies primarily on natural language. While this design…

Artificial Intelligence · Computer Science 2025-06-04 Pengcheng Zhou , Yinglun Feng , Halimulati Julaiti , Zhongliang Yang

Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state…

Computation and Language · Computer Science 2026-05-19 Tianxiang Dai , Jonathan Fan

Agents in the real world must make not only logical but also timely judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still…

Artificial Intelligence · Computer Science 2025-11-10 Yule Wen , Yixin Ye , Yanzhe Zhang , Diyi Yang , Hao Zhu

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often…

Artificial Intelligence · Computer Science 2026-05-27 Yuxin Chen , Xiaodong Cai , Junfeng Fang , Zhuowen Han , Yu Wang , Yaorui Shi , Yi Zhang , Qi Gu , Xunliang Cai , Xiang Wang , An Zhang , Tat-Seng Chua

Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as an organizational abstraction, but we argue it is also a…

Artificial Intelligence · Computer Science 2026-05-14 Shawn Li , Chenxiao Yu , Han Wang , Wei Yang , Ryan Rossi , Franck Dernoncourt , Xiyang Hu , Philip Yu , Chaowei Xiao , Huan Zhang , Yue Zhao

Flocking is a behavior where multiple agents in a system attempt to stay close to each other while avoiding collision and maintaining a desired formation. This is observed in the natural world and has applications in robotics, including…

Artificial Intelligence · Computer Science 2024-12-18 Peihan Li , Vishnu Menon , Bhavanaraj Gudiguntla , Daniel Ting , Lifeng Zhou