Search Results for "ai code agent"

AlphaGeometry, developed by Google DeepMind, is a theorem-proving system that combines symbolic reasoning with deep learning to solve challenging geometry problems, such as those found in mathematical Olympiads. The repository provides the full implementation of DDAR (Deductive Difference and Abductive Reasoning) and AlphaGeometry, two automated geometry solvers described in the 2024 Nature paper “Solving Olympiad Geometry without Human Demonstrations.” AlphaGeometry integrates a symbolic...

PortOpt [Portfolio Optimizer] is a C++ program (with Python binding) implementing the Markowitz(1952) mean-variance model with agent's linear indifference curves toward risk in order to find the optimal assets portfolio under risk. You have to provide PortOpt (in text files or - if you use the api - using your own code) the variance/covariance matrix of the assets, their average returns and the agent risk preference. It returns the vector of assets' shares that composes the optimal portfolio. In order to minimise the variance it internally uses QuadProg++, a library that implement the algorithm of Goldfarb and Idnani for the solution of a (convex) Quadratic Programming problem by means of an active-set dual method. ...

MASyV (Multi-Agent System Visualization) enables one to write agent-based models/cellular automata, eg. in C, visualize them in real time & capture to movie file with MASyVs GUI & message passing lib. Includes examples: Hello World, ants, viral infection

Don't hard-code data-structures for Artificial Intelligence (AI). Evolve them (and control flow) as cycles of arrays in arrays with size constraints based on other array sizes (at specific index) in terms of range, multiply, exponent, or permutation. No working code yet. Whats there now is an extension of GigaLineCompile which would become part of Human AI Net, but there are other projects to finish before I can come back to this one.

Anarchonomy is a Java application simulating AI agent based production, consumption, trade and force with a minimum of economic assumptions, letting users create and change their own rule and scenario sets.