Related papers: Specialists and Generalists: Equilibrium Skill Acq…

Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environment scaling: expanding the distribution of executable…

Rationality is often related to optimal decision making. Humans are known to be bounded rational agents. However, recent advances in computing, and other scientific and technical fields along with large amount of data have led to a feeling…

The potential of large language models (LLMs) to reason like humans has been a highly contested topic in Machine Learning communities. However, the reasoning abilities of humans are multifaceted and can be seen in various forms, including…

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to…

We attempt to define what is necessary to construct an Artificial Scientist, explore and evaluate several approaches to artificial general intelligence (AGI) which may facilitate this, conclude that a unified or hybrid approach is necessary…

In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great…

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling…

The capacity to generalize beyond the range of training data is a pivotal challenge, often synonymous with a model's utility and robustness. This study investigates the comparative abilities of traditional machine learning (ML) models and…

Human experts are often engaged in the development of machine learning systems to collect and validate data, consult on algorithm development, and evaluate system performance. At the same time, who counts as an 'expert' and what constitutes…

Cooperation and defection may be considered as two extreme responses to a social dilemma. Yet the reality is much less clear-cut. Between the two extremes lies an interval of ambivalent choices, which may be captured theoretically by means…

When information acquisition is costly but flexible, a principal may rationally acquire information that favors one group over another. The former group faces incentives to invest in becoming productive, while the latter is discouraged from…

The growing integration of large language models across professional domains transforms how experts make critical decisions in healthcare, education, and law. While significant research effort focuses on getting these systems to communicate…

Consider multiple experts with overlapping expertise working on a classification problem under uncertain input. What constitutes a consistent set of opinions? How can we predict the opinions of experts on missing sub-domains? In this paper,…

The ability to categorize problems is a measure of expertise in a domain. In order to help students learn effectively, instructors and teaching assistants (TAs) should have pedagogical content knowledge. They must be aware of the prior…

People often engage in costly cooperation, especially in repeated interactions. When deciding whether to cooperate, individuals typically take into account how others have acted in the past. For instance, when one person is deciding whether…

Generative AI's novel capacities raise questions about the future role of human expertise: does AI level the playing field between professional artists and laypeople, or does expertise enhance AI use? Do the cognitive skills experts make…

Numerous studies and anecdotes demonstrate the "wisdom of the crowd," the surprising accuracy of a group's aggregated judgments. Less is known, however, about the generality of crowd wisdom. For example, are crowds wise even if their…

Behavioral cloning is a simple yet effective technique for learning sequential decision-making from demonstrations. Recently, it has gained prominence as the core of foundation models for the physical world, where achieving generalization…

Decision theory recognizes two principal approaches to solving problems under uncertainty: probabilistic models and cognitive heuristics. However, engineers, public planners and decision-makers in other fields seem to employ solution…

In order to solve today's complex problems in the world of software development, technical knowledge is no longer enough. Previous studies investigating and identifying non-technical skills of software engineers show that creative skills…