English
Related papers

Related papers: CoinRun: Solving Goal Misgeneralisation

200 papers

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of…

Current AI alignment methodologies rely on human-provided demonstrations or judgments, and the learned capabilities of AI systems would be upper-bounded by human capabilities as a result. This raises a challenging research question: How can…

Machine Learning · Computer Science 2024-12-11 Zhiqing Sun , Longhui Yu , Yikang Shen , Weiyang Liu , Yiming Yang , Sean Welleck , Chuang Gan

In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities. In this paper, we consider the problem where an autonomous agent needs to act in a…

Artificial Intelligence · Computer Science 2020-01-27 Anagha Kulkarni , Siddharth Srivastava , Subbarao Kambhampati

In this comprehensive review, we describe a new mathematical problem in artificial intelligence (AI) from a mathematical modeling perspective, following the philosophy stated by Rudolf E. Kalman that "Once you get the physics right, the…

Artificial Intelligence · Computer Science 2020-11-13 Bao-Gang Hu , Han-Bing Qu

As general purpose vision models get increasingly effective at a wide set of tasks, it is imperative that they be consistent across the tasks they support. Inconsistent AI models are considered brittle and untrustworthy by human users and…

Computer Vision and Pattern Recognition · Computer Science 2024-02-23 Adyasha Maharana , Amita Kamath , Christopher Clark , Mohit Bansal , Aniruddha Kembhavi

Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures…

Computer Vision and Pattern Recognition · Computer Science 2023-02-17 André Susano Pinto , Alexander Kolesnikov , Yuge Shi , Lucas Beyer , Xiaohua Zhai

Empowering embodied agents, such as robots, with Artificial Intelligence (AI) has become increasingly important in recent years. A major challenge is task open-endedness. In practice, robots often need to perform tasks with novel goals that…

Artificial Intelligence · Computer Science 2023-12-12 William Wei Wang , Dongqi Han , Xufang Luo , Yifei Shen , Charles Ling , Boyu Wang , Dongsheng Li

Building meaningful interoperation with external software units requires performing the conceptual interoperability analysis that starts with identifying the conceptual interoperability constraints of each software unit, then it compares…

Software Engineering · Computer Science 2018-12-06 Hadil Abukwaik , Mohammed Abufouda , Thejashree Nair , Dieter Rombach

Creating systems that are aligned with our goals is seen as a leading approach to create safe and beneficial AI in both leading AI companies and the academic field of AI safety. We defend the view that misaligned AGI - future, generally…

Computers and Society · Computer Science 2025-06-05 Max Hellrigel-Holderbaum , Leonard Dung

Artificial currencies have grown in popularity in many real-world resource allocation settings, gaining traction in government benefits programs like food assistance and transit benefits programs. However, such programs are susceptible to…

Systems and Control · Electrical Eng. & Systems 2024-02-27 Devansh Jalota , Matthew Tsao , Marco Pavone

We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…

Artificial Intelligence · Computer Science 2025-11-20 Aran Nayebi

Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such misaligned actions may arise from external attacks (e.g.,…

Computation and Language · Computer Science 2026-02-10 Yuting Ning , Jaylen Jones , Zhehao Zhang , Chentao Ye , Weitong Ruan , Junyi Li , Rahul Gupta , Huan Sun

Deep neural networks are notoriously sensitive to spurious correlations - where a model learns a shortcut that fails out-of-distribution. Existing work on spurious correlations has often focused on incomplete correlations,leveraging access…

The AI research community plays a vital role in shaping the scientific, engineering, and societal goals of AI research. In this position paper, we argue that focusing on the highly contested topic of `artificial general intelligence'…

Goal instructions for autonomous AI agents cannot assume that objects have unique names. Instead, objects in goals must be referred to by providing suitable descriptions. However, this raises problems in both classical planning and…

Artificial Intelligence · Computer Science 2024-10-01 Martin Funkquist , Simon Ståhlberg , Hector Geffner

One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person's goal(s). Existing methods tend to rely on inferring the human's goal, which is challenging when there…

Artificial Intelligence · Computer Science 2021-01-11 Yuqing Du , Stas Tiomkin , Emre Kiciman , Daniel Polani , Pieter Abbeel , Anca Dragan

As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task scope. It is therefore important to understand how extremely capable AI models will fail: Will…

Artificial Intelligence · Computer Science 2026-04-13 Alexander Hägele , Aryo Pradipta Gema , Henry Sleight , Ethan Perez , Jascha Sohl-Dickstein

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive…

Computers and Society · Computer Science 2020-10-07 Iason Gabriel

We suggest that the analysis of incomplete contracting developed by law and economics researchers can provide a useful framework for understanding the AI alignment problem and help to generate a systematic approach to finding solutions. We…

Artificial Intelligence · Computer Science 2018-04-13 Dylan Hadfield-Menell , Gillian Hadfield

Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…

Machine Learning · Computer Science 2024-01-18 Sunayana Rane , Polyphony J. Bruna , Ilia Sucholutsky , Christopher Kello , Thomas L. Griffiths