richards199999 / Self-Iterative-Agent-System-for-Complex-Problem-Solving

Multiple instructed-LLMs engage in multi-round "self-questioning" to seek the optimal solution, borrowing from the idea of debate, iteratively refining the current problem-solving process, and finally selecting the optimal solution to give a conclusion.
64Updated 3 months ago

Related projects

Alternatives and complementary repositories for Self-Iterative-Agent-System-for-Complex-Problem-Solving