paper-with-me

Papers

Artificial Expert Intelligence through PAC-reasoning

2024-12-03 · Shai Shalev-Shwartz, Amnon Shashua, Gal Beniamini, Yoav Levine, Or Sharir, Noam Wies, Ido Ben-Shaul, Tomer Nussbaum, Shir Granot Peled

Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts. Existing AI systems often excel at predefined tasks but struggle with adaptability and precision in novel problem-solving. To overcome this, AEI introduces a framework for ``Probably Approximately Correct (PAC) Reasoning". This paradigm provides robust theoretical guarantees for reliably decomposing complex problems, with a practical mechanism for controlling reasoning precision. In reference to the division of human thought into System 1 for intuitive thinking and System 2 for reflective reasoning~\citep{tversky1974judgment}, we refer to this new type of reasoning as System 3 for precise reasoning, inspired by the rigor of the scientific method. AEI thus establishes a foundation for error-bounded, inference-time learning.

📄 PDF Abstract BibTeX arXiv:2412.02441

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Emergence is Overrated: AGI as an Archipelago of Experts

2026-03-09 · Daniel Kilov arxiv

Krakauer, Krakauer, and Mitchell (2025) distinguish between emergent capabilities and emergent intelligence, arguing that true intelligence requires efficient coarse-grained representations enabling diverse problem-solvi…

Development of an Adaptive Multi-Domain Artificial Intelligence System Built using Machine Learning and Expert Systems Technologies

2024-06-17 · Jeremy Straub

Producing an artificial general intelligence (AGI) has been an elusive goal in artificial intelligence (AI) research for some time. An AGI would have the capability, like a human, to be exposed to a new problem domain, l…

Decision Making

DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker

2017-01-06 · Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý 외

Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker is the quintessential game o…

Game of Poker

LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence

2025-12-04 · Wenjin Liu, Haoran Luo, Xin Feng, Xiang Ji 외 arxiv

Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulating the expertise of legal experts across domains. However, existing ben…

Neural-Base Music Generation for Intelligence Duplication

2023-10-20 · Jacob Galajda, Kien Hua

There are two aspects of machine learning and artificial intelligence: (1) interpreting information, and (2) inventing new useful information. Much advance has been made for (1) with a focus on pattern recognition techni…

Music Generation