English
Related papers

Related papers: Misalignment Bounty: Crowdsourcing AI Agent Misbeh…

200 papers

It is hypothesized by some thinkers that benign looking AI objectives may result in powerful AI drives that may pose an existential risk to human society. We analyze this scenario and find the underlying assumptions to be unlikely. We…

Artificial Intelligence · Computer Science 2016-10-12 Eray Özkural

Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…

Artificial Intelligence · Computer Science 2025-01-17 Vivek Myers , Evan Ellis , Sergey Levine , Benjamin Eysenbach , Anca Dragan

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,…

Computers and Society · Computer Science 2024-08-14 Joseph Carlsmith

Recent years have seen an emerging interest in the trustworthiness of machine learning-based agents in the wild, especially in robotics, to provide safety assurance for the industry. Obtaining behavioral guarantees for these agents remains…

Artificial Intelligence · Computer Science 2024-02-22 Zhiyu An , Xianzhong Ding , Wan Du

Most AI systems today are designed to manage tasks and execute predefined steps. This makes them effective for process coordination but limited in their ability to engage in joint problem-solving with humans or contribute new ideas. We…

Human-Computer Interaction · Computer Science 2026-02-03 Kexin Quan , Dina Albassam , Mengke Wu , Zijian Ding , Jessie Chin

Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…

Computers and Society · Computer Science 2022-07-05 John Nay , James Daily

We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solve complex tasks, they often fail because agents act…

Artificial Intelligence · Computer Science 2026-05-26 Wenqian Ye , Bo Yuan , Zhichao Xu , Yijun Tian , Yawei Wang , Henry Kautz , Aidong Zhang

Crowdsourced machine learning on competition platforms such as Kaggle is a popular and often effective method for generating accurate models. Typically, teams vie for the most accurate model, as measured by overall error on a holdout set,…

Machine Learning · Computer Science 2024-02-19 Ira Globus-Harris , Declan Harrison , Michael Kearns , Pietro Perona , Aaron Roth

Recent research in multi-agent reinforcement learning (MARL) has shown success in learning social behavior and cooperation. Social dilemmas between agents in mixed-sum settings have been studied extensively, but there is little research…

Artificial Intelligence · Computer Science 2023-05-01 Ram Rachum , Yonatan Nakar , Reuth Mirsky

Reaching agreement despite noise in communication is a fundamental problem in multi-agent systems. Here we study this problem under an idealized model, where it is assumed that agents can sense the general tendency in the system. More…

Computer Science and Game Theory · Computer Science 2023-01-09 Amos Korman , Robin Vacus

This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexist in a common environment. Unlike in the case of requested…

Artificial Intelligence · Computer Science 2021-09-07 Anagha Kulkarni , Siddharth Srivastava , Subbarao Kambhampati

Just as people improve decision-making by consulting diverse human advisors, they can now also consult with multiple AI systems. Prior work on group decision-making shows that advice aggregation creates pressure to conform, leading to…

Human-Computer Interaction · Computer Science 2026-03-24 Yuta Tsuchiya , Yukino Baba

Given two sources of evidence about a latent variable, one can combine the information from both by multiplying the likelihoods of each piece of evidence. However, when one or both of the observation models are misspecified, the…

Machine Learning · Computer Science 2021-03-24 Dmitrii Krasheninnikov , Rohin Shah , Herke van Hoof

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of the art reinforcement learning algorithms often suffer from…

Multiagent Systems · Computer Science 2021-05-17 Woodrow Z. Wang , Mark Beliaev , Erdem Bıyık , Daniel A. Lazar , Ramtin Pedarsani , Dorsa Sadigh

Recent work has shown that, in classification tasks, it is possible to design decision support systems that do not require human experts to understand when to cede agency to a classifier or when to exercise their own agency to achieve…

Machine Learning · Computer Science 2025-10-21 Eleni Straitouri , Stratis Tsirtsis , Ander Artola Velasco , Manuel Gomez-Rodriguez

Reward function, as an incentive representation that recognizes humans' agency and rationalizes humans' actions, is particularly appealing for modeling human behavior in human-robot interaction. Inverse Reinforcement Learning is an…

Artificial Intelligence · Computer Science 2021-03-09 Ran Tian , Masayoshi Tomizuka , Liting Sun

We investigate whether and why people might adjust compensation for workers who use AI tools. Across 13 studies (N = 4,956), participants consistently lowered compensation for workers who used AI compared to those who did not. This "AI…

General Economics · Economics 2026-03-06 Jin Kim , Shane Schweitzer , David De Cremer , Christoph Riedl

In this chapter we look at one of the canonical driving examples for multi-agent systems: average consensus. In this scenario, a group of agents seek to agree on the average of their initial states. Depending on the particular application,…

Optimization and Control · Mathematics 2016-09-23 Cameron Nowzari , Jorge Cortes , George J. Pappas

AI agents have been evaluated in isolation or within small groups, where interactions remain limited in scope and complexity. Large-scale simulations involving many autonomous agents -- reflecting the full spectrum of civilizational…