如何评估通用人工智能(Artificial General Intelligence,AGI)是一个长期被讨论却悬而未决的关键问题。在窄人工智能(narrow AI)研究中,这似乎算不上严峻问题,因为该领域的研究者聚焦于特定问题以及认知的一个或若干方面,且评估标准有明确的定义。相比之下,AGI智能体应当能解决智能体和开发者都从未遇到过的问题。然而,一旦开发者用某个问题对智能体进行测试和调试,这个从未遇到的问题就变成了已遇到的问题,如此一来,问题在一定程度上是开发者利用自身经验解决的,而非智能体独立解决。我们将这一矛盾称为“开发者经验陷阱”,它导致这类问题很难成为公认的评估标准。\n本文提出了一种名为“人工开放世界(Artificial Open World)”的评估方法,旨在跳出这一陷阱。其核心思路是:现实世界中的大部分经验不必适用于人工世界,且该世界在某种意义上应当是开放的,使得开发者在测试前无法感知这个世界、也无法自行解决其中的问题,但测试后他们可以查看所有数据。该世界以与现实世界相似的方式生成,本文还提出了问题的通用形式,并设计了一项旨在量化研究进展的指标。本文阐述了人工开放世界的概念设计,其形式化与实现工作将留待未来开展。
英文摘要:
How to evaluate Artificial General Intelligence (AGI) is a critical problem that is discussed and unsolved for a long period. In the research of narrow AI, this seems not a severe problem, since researchers in that field focus on some specific problems as well as one or some aspects of cognition, and the criteria for evaluation are explicitly defined. By contrast, an AGI agent should solve problems that are never-encountered by both agents and developers. However, once a developer tests and debugs the agent with a problem, the never-encountered problem becomes the encountered problem, as a result, the problem is solved by the developers to some extent, exploiting their experience, rather than the agents. This conflict, as we call the trap of developers' experience, leads to that this kind of problems is probably hard to become an acknowledged criterion. In this paper, we propose an evaluation method named Artificial Open World, aiming to jump out of the trap. The intuition is that most of the experience in the actual world should not be necessary to be applied to the artificial world, and the world should be open in some sense, such that developers are unable to perceive the world and solve problems by themselves before testing, though after that they are allowed to check all the data. The world is generated in a similar way as the actual world, and a general form of problems is proposed. A metric is proposed aiming to quantify the progress of research. This paper describes the conceptual design of the Artificial Open World, though the formalization and the implementation are left to the future.
Evaluating Multimodal Large Language Models with Daily Composite Tasks in Home Environments
State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence(通用人工智能国家重点实验室、北京通用人工智能研究院);School of Psychological and Cognitive Sciences and Beijing Key Laboratory of Behavior and Mental Health, Key Laboratory of Machine Perception (Ministry of Education), Peking University(心理与认知科学学院及北京行为与心理健康重点实验室、机器感知重点实验室(教育部));School of Intelligence Science and Technology, Peking University(智能科学与技术学院)
Personalized Artificial General Intelligence (AGI) via Neuroscience-Inspired Continuous Learning Systems
Department of AI and Robotics, IGNITE Pathways(人工智能与机器人系,IGNITE路径);Department of Youth Wellness and Research, Neuro Health Alliance(青年健康与研究系,神经健康联盟);Medical Director of JFK Neuroscience Sleep Center, HMH-JFK Neuroscience Institute(JFK神经睡眠中心医疗总监,HMH-JFK神经科学研究所)
Optimising for Flourishing: Flourishing Metrics and Return on Flourishing as Success Criteria for Artificial Intelligence and Post-AGI Economic Systems
Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory
Visa Research(Visa研究院);Microsoft Research Montréal(微软蒙特利尔研究院);Johns Hopkins University(约翰斯·霍普金斯大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
Saarland University(萨尔大学);Technical University Dortmund(多特蒙德工业大学);Institute of Intelligent Software(智能软件研究所)
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
Department of Computing Technologies(计算技术系);SRM Institute of Science and Technology(SRM科学与技术学院);Bio-Sensing and Bio-Sensors Group(生物传感与生物传感器组);Smart Automation and Communication Technologies Research Institute of Sciences and Engineering(科学与工程智能自动化与通信技术研究所);University of Sharjah, UAE(阿联酋沙迦大学);Department of Computer Engineering(计算机工程系);College of Computing and Informatics(计算与信息学院)