Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Deductive Reasoning01:16

Deductive Reasoning

63.7K
Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...
63.7K
Reasoning01:30

Reasoning

388
Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
388
Inductive Reasoning00:59

Inductive Reasoning

64.5K
Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
64.5K
Observational Learning01:12

Observational Learning

804
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
804
Reinforcement01:23

Reinforcement

804
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
804
Theorems of Pappus and Guldinus: Problem Solving01:12

Theorems of Pappus and Guldinus: Problem Solving

1.0K
Pappus and Guldinus's theorems are powerful mathematical principles that are used for finding the surface area and volume of composite shapes. For example, consider a cylindrical storage tank with a conical top. Finding the surface area or volume can be challenging for such complex shapes. These theorems are particularly useful in calculating the volume and surface area of such systems. Here, the cylindrical storage tank with a conical top can be broken down into two simple shapes: a...
1.0K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Lipid nanoparticles for Cas9 ribonucleoprotein delivery: design and evaluation of ionisable oligoamine-lipidoids.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2026
Same author

Accelerating scientific discovery with Co-Scientist.

Nature·2026
Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026
Same author

Advancing regulatory variant effect prediction with AlphaGenome.

Nature·2026
Same author

Tumor Microenvironment Reprogramming via Copper-Enriched Black Phosphorus Nanoplatform for Cuproptosis-Sensitized Low-Dose Radioimmunotherapy.

International journal of nanomedicine·2025
Same author

Acute Toxicities and Early Outcomes of Tandem Autologous Stem Cell Transplantation in Pediatric High-Risk Neuroblastoma: A Multicenter Study.

Transplantation and cellular therapy·2025

Related Experiment Video

Updated: Jan 11, 2026

Exploring the Role of Deontic Reasoning and World Knowledge in Wason´s Selection Task
06:08

Exploring the Role of Deontic Reasoning and World Knowledge in Wason´s Selection Task

Published on: July 22, 2025

814

Olympiad-level formal mathematical reasoning with reinforcement learning.

Thomas Hubert1, Rishi Mehta2, Laurent Sartran2

  • 1Google DeepMind, London, UK. tkhubert@google.com.

Nature
|November 12, 2025
PubMed
Summary
This summary is machine-generated.

AlphaProof, an AI agent, learns complex mathematical reasoning through reinforcement learning (RL) and formal proofs. This system achieved medal-level performance at the IMO competition, demonstrating AI

More Related Videos

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents
09:01

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

13.1K
Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
07:01

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment

Published on: September 20, 2020

5.2K

Related Experiment Videos

Last Updated: Jan 11, 2026

Exploring the Role of Deontic Reasoning and World Knowledge in Wason´s Selection Task
06:08

Exploring the Role of Deontic Reasoning and World Knowledge in Wason´s Selection Task

Published on: July 22, 2025

814
The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents
09:01

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

13.1K
Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
07:01

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment

Published on: September 20, 2020

5.2K

Area of Science:

  • Artificial Intelligence
  • Formal Methods
  • Reinforcement Learning

Background:

  • Current AI systems often lack formal verification for mathematical reasoning.
  • Formal languages like Lean provide grounded reasoning environments.
  • Reinforcement learning (RL) offers a mechanism for learning in interactive environments.

Purpose of the Study:

  • To develop an AI system capable of complex mathematical reasoning and formal proof generation.
  • To leverage RL for learning proof strategies in formal mathematical domains.
  • To improve AI performance on challenging mathematical problems.

Main Methods:

  • Developed AlphaProof, an AlphaZero-inspired agent utilizing RL for formal proof discovery.
  • Trained AlphaProof on millions of auto-formalized mathematical problems.
  • Employed Test-Time RL for problem-specific adaptation on difficult problems.

Main Results:

  • AlphaProof significantly advanced state-of-the-art results on historical mathematics competition problems.
  • The AI system solved three out of five non-geometry problems at the 2024 IMO competition, including the most difficult one.
  • Combined with AlphaGeometry 2, the AI achieved a silver medallist equivalent score, a first for AI in medal-level performance.

Conclusions:

  • Large-scale learning from grounded experience enables AI agents with sophisticated mathematical reasoning.
  • AlphaProof demonstrates the potential of reliable AI tools for complex mathematical problem-solving.
  • This work paves the way for AI systems to tackle intricate mathematical challenges.