中文
相关论文

相关论文: Designing for Human-Agent Alignment: Understanding…

200 篇论文

Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios…

人工智能 · 计算机科学 2025-11-19 Steven J. Jones , Robert E. Wray , John E. Laird

This survey paper examines the recent advancements in AI agent implementations, with a focus on their ability to achieve complex goals that require enhanced reasoning, planning, and tool execution capabilities. The primary objectives of…

人工智能 · 计算机科学 2024-04-18 Tula Masterman , Sandi Besen , Mason Sawtell , Alex Chao

Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment in the context of…

人工智能 · 计算机科学 2024-11-19 Parand A. Alamdari , Toryn Q. Klassen , Rodrigo Toro Icarte , Sheila A. McIlraith

AI intent alignment, ensuring that AI produces outcomes as intended by users, is a critical challenge in human-AI interaction. The emergence of generative AI, including LLMs, has intensified the significance of this problem, as interactions…

人机交互 · 计算机科学 2024-06-21 Yoonsu Kim , Kihoon Son , Seoyoung Kim , Juho Kim

Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align…

计算机与社会 · 计算机科学 2025-01-23 Kush R. Varshney , Zahra Ashktorab , Djallel Bouneffouf , Matthew Riemer , Justin D. Weisz

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and…

Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility…

人工智能 · 计算机科学 2024-02-16 Paulo Garcia

Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…

人工智能 · 计算机科学 2023-02-10 Malek Mechergui , Sarath Sreedharan

Existing work on the alignment problem has focused mainly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing…

多智能体系统 · 计算机科学 2025-06-03 Aidan Kierans , Avijit Ghosh , Hananel Hazan , Shiri Dori-Hacohen

As designers become familiar with Generative AI, a new concept is emerging: Agentic AI. While generative AI produces output in response to prompts, agentic AI systems promise to perform mundane tasks autonomously, potentially freeing…

人机交互 · 计算机科学 2025-09-26 Samangi Wadinambiarachchi , Jenny Waycott , Yvonne Rogers , Greg Wadley

AI agents are increasingly developed and evaluated on benchmarks relevant to human work, yet it remains unclear how representative these benchmarking efforts are of the labor market as a whole. In this work, we systematically study the…

Negotiation is a complex social interaction that encapsulates emotional encounters in human decision-making. Virtual agents that can negotiate with humans are useful in pedagogy and conversational AI. To advance the development of such…

人机交互 · 计算机科学 2021-07-29 Kushal Chawla , Rene Clever , Jaysa Ramirez , Gale Lucas , Jonathan Gratch

Managing one's digital footprint is overwhelming, as it spans multiple platforms and involves countless context-dependent decisions. Recent advances in agentic AI offer ways forward by enabling holistic, contextual privacy-enhancing…

人机交互 · 计算机科学 2026-02-12 Eryue Xu , Tianshi Li

This empirical study serves as a primer for interested service providers to determine if and how Large Language Models (LLMs) technology will be integrated for their practitioners and the broader community. We investigate the mutual…

人机交互 · 计算机科学 2023-12-01 Qingxiao Zheng , Zhongwei Xu , Abhinav Choudhry , Yuting Chen , Yongming Li , Yun Huang

In the rapidly evolving field of artificial intelligence (AI) agents, designing the agent's characteristics is crucial for shaping user experience. This workshop aims to establish a research community focused on AI agent persona design for…

人机交互 · 计算机科学 2024-10-31 Nima Zargham , Mateusz Dubiel , Smit Desai , Thomas Mildner , Hanz-Joachim Belz

Agency, the capacity to proactively shape events, is central to how humans interact and collaborate. While LLMs are being developed to simulate human behavior and serve as human-like agents, little attention has been given to the Agency…

计算与语言 · 计算机科学 2024-02-09 Ashish Sharma , Sudha Rao , Chris Brockett , Akanksha Malhotra , Nebojsa Jojic , Bill Dolan

Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up…

人工智能 · 计算机科学 2018-01-31 Tathagata Chakraborti , Subbarao Kambhampati

AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…

计算机与社会 · 计算机科学 2025-12-02 K. J. Kevin Feng , Tae Soo Kim , Rock Yuren Pang , Faria Huq , Tal August , Amy X. Zhang

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by…

人工智能 · 计算机科学 2021-03-30 Zachary Kenton , Tom Everitt , Laura Weidinger , Iason Gabriel , Vladimir Mikulik , Geoffrey Irving

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…

机器学习 · 计算机科学 2018-11-20 Jan Leike , David Krueger , Tom Everitt , Miljan Martic , Vishal Maini , Shane Legg