English
Related papers

Related papers: A Sober Look at Agentic Misalignment in Automated …

200 papers

Misalignment in Multi-Agent Systems (MAS) is frequently treated as a technical failure. Yet, issues may arise from the conceptual design phase, where semantic ambiguity and normative projection occur. The Rabbit-Duck illusion illustrates…

Multiagent Systems · Computer Science 2025-12-23 Shayak Nandi , Fernanda M. Eliott

As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents…

Multiagent Systems · Computer Science 2025-04-08 Sagar Tamang , Dibya Jyoti Bora

Multi-agent behavior modeling and trajectory forecasting are crucial for the safe navigation of autonomous agents in interactive scenarios. Variational Autoencoder (VAE) has been widely applied in multi-agent interaction modeling to…

Machine Learning · Computer Science 2021-12-02 Chen Tang , Wei Zhan , Masayoshi Tomizuka

Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is severely hampered by the challenge of failure attribution. Current diagnostic tools, which rely on statistical correlations, are…

Artificial Intelligence · Computer Science 2025-09-11 Guoqing Ma , Jia Zhu , Hanghui Guo , Weijie Shi , Jiawei Shen , Jingjiang Liu , Yidan Liang

With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a…

Computers and Society · Computer Science 2025-09-03 Yuan-Hao Jiang , Yijie Lu , Ling Dai , Jiatong Wang , Ruijia Li , Bo Jiang

As Multi Agent Reinforcement Learning systems are used in safety critical applications. Understanding why agents make decisions and how they achieve collective behavior is crucial. Existing explainable AI methods struggle in multi agent…

Artificial Intelligence · Computer Science 2025-11-21 Abraham Itzhak Weinberg

Recent embedding-based methods have achieved great successes in exploiting entity alignment from knowledge graph (KG) embeddings of multiple modalities. In this paper, we study embedding-based entity alignment (EEA) from a perspective of…

Computation and Language · Computer Science 2024-02-27 Lingbing Guo , Zhuo Chen , Jiaoyan Chen , Yin Fang , Wen Zhang , Huajun Chen

Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…

Computation and Language · Computer Science 2026-02-23 Ali El Filali , Inès Bedar

Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for reliable multimodal systems. Yet existing evaluation paradigms for vision-language models (VLMs) and multi-agent systems (MAS)…

Computation and Language · Computer Science 2026-04-17 Nishanth Madhusudhan , Vikas Yadav , Alexandre Lacoste

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business…

Over the years, research in system identification has provided a rich set of methods for learning dynamical models, together with well-established theoretical guarantees. In practice, however, the choice of model class, training algorithm,…

Artificial Intelligence · Computer Science 2026-05-12 Dario Piga , Marco Forgione

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

Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to…

Artificial Intelligence · Computer Science 2026-04-14 Anushree Sinha , Srivaths Ranganathan , Debanshu Das , Abhishek Dharmaratnakar

The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in…

Artificial Intelligence · Computer Science 2024-09-12 Mehrdad Zakershahrak , Samira Ghodratnama

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…

Physics and Society · Physics 2026-05-12 Giordano De Marzo , Alessandro Bellina , Claudio Castellano , Viola Priesemann , David Garcia

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either…

Multiagent Systems · Computer Science 2026-05-26 Haoran Li , Shulun Chen , Shaoyuan Sun , Hanchen Wang

Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, and to the best of…

Computation and Language · Computer Science 2025-02-12 Yaming Yang , Zhe Wang , Ziyu Guan , Wei Zhao , Weigang Lu , Xinyan Huang , Jiangtao Cui , Xiaofei He

General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…

Computation and Language · Computer Science 2026-05-19 Han Bao , Yue Huang , Xiaoda Wang , Zheyuan Zhang , Yujun Zhou , Carl Yang , Xiangliang Zhang , Yanfang Ye

Recently, we have proposed a framework for verification of agents' abilities in asynchronous multi-agent systems, together with an algorithm for automated reduction of models. The semantics was built on the modeling tradition of distributed…

Logic in Computer Science · Computer Science 2025-01-22 Wojciech Jamroga , Wojciech Penczek , Teofil Sidoruk

In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a…

Multiagent Systems · Computer Science 2025-05-08 Stéphane Aroca-Ouellette , Miguel Aroca-Ouellette , Katharina von der Wense , Alessandro Roncone