Related papers: Counting Cycles with Deepseek

Counting Cycles with Deepseek

URL: http://arxiv.org/abs/2505.17964v1
Date: Fri, 23 May 2025 14:34:40 GMT
Title: Counting Cycles with Deepseek
Authors: Jiashun Jin, Tracy Ke, Bingcheng Sui, Zhenggang Wang,
Abstract summary: We consider a difficult open problem: How to derive a Computationally Efficient Equivalent Form (CEEF) for the cycle count statistic.<n>We combine a novel approach we propose and the powerful coding skills of AI to solve the problem.<n>We find that, while AI is unable to solve the problem all by itself, it is able to solve it if we provide it with a clear strategy, a step-by-step guidance and carefully written prompts.
Score: 10.137124603866038
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Despite recent progress, AI still struggles on advanced mathematics. We consider a difficult open problem: How to derive a Computationally Efficient Equivalent Form (CEEF) for the cycle count statistic? The CEEF problem does not have known general solutions, and requires delicate combinatorics and tedious calculations. Such a task is hard to accomplish by humans but is an ideal example where AI can be very helpful. We solve the problem by combining a novel approach we propose and the powerful coding skills of AI. Our results use delicate graph theory and contain new formulas for general cases that have not been discovered before. We find that, while AI is unable to solve the problem all by itself, it is able to solve it if we provide it with a clear strategy, a step-by-step guidance and carefully written prompts. For simplicity, we focus our study on DeepSeek-R1 but we also investigate other AI approaches.

Related papers

In between myth and reality: AI for math -- a case study in category theory [0.0]
We discuss an experiment we have made in the direction of mathematical research, with two of the most prominent contemporary AI systems.<n>One of the objective of this experiment is to get an understanding of how AI systems can assist mathematical research.
arXiv Detail & Related papers (2025-04-17T21:58:30Z)
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
o1-like models can emulate human-like long-time thinking during inference.<n>This paper presents the first comprehensive study on the prevalent issue of overthinking in these models.<n>We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
arXiv Detail & Related papers (2024-12-30T18:55:12Z)
Formal Mathematical Reasoning: A New Frontier in AI [60.26950681543385]
We advocate for formal mathematical reasoning and argue that it is indispensable for advancing AI4Math to the next level.<n>We summarize existing progress, discuss open challenges, and envision critical milestones to measure future success.
arXiv Detail & Related papers (2024-12-20T17:19:24Z)
AI for Mathematics: A Cognitive Science Perspective [86.02346372284292]
Mathematics is one of the most powerful conceptual systems developed and used by the human species. Rapid progress in AI, particularly propelled by advances in large language models (LLMs), has sparked renewed, widespread interest in building such systems.
arXiv Detail & Related papers (2023-10-19T02:00:31Z)
Problem-Solving Guide: Predicting the Algorithm Tags and Difficulty for Competitive Programming Problems [7.955313479061445]
Most tech companies require the ability to solve algorithm problems including Google, Meta, and Amazon. Our study addresses the task of predicting the algorithm tag as a useful tool for engineers and developers. We also consider predicting the difficulty levels of algorithm problems, which can be used as useful guidance to calculate the required time to solve that problem.
arXiv Detail & Related papers (2023-10-09T15:26:07Z)
Exceeding Computational Complexity Trial-and-Error Dynamic Action and Intelligence [0.0]
Computational complexity is a core theory of computer science, which dictates the degree of difficulty of computation. In this paper, we try to clarify concepts, and we propose definitions such as unparticularized computing, particularized computing, computing agents, and dynamic search. We also propose and discuss a framework, i.e., trial-and-error + dynamic search.
arXiv Detail & Related papers (2022-12-22T21:23:27Z)
Divide & Conquer Imitation Learning [75.31752559017978]
Imitation Learning can be a powerful approach to bootstrap the learning process. We present a novel algorithm designed to imitate complex robotic tasks from the states of an expert trajectory. We show that our method imitates a non-holonomic navigation task and scales to a complex simulated robotic manipulation task with very high sample efficiency.
arXiv Detail & Related papers (2022-04-15T09:56:50Z)
End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking [52.05847268235338]
We show how machine learning systems can perform logical extrapolation without overthinking problems. We propose a recall architecture that keeps an explicit copy of the problem instance in memory so that it cannot be forgotten. We also employ a progressive training routine that prevents the model from learning behaviors that are specific to number and instead pushes it to learn behaviors that can be repeated indefinitely.
arXiv Detail & Related papers (2022-02-11T18:43:28Z)
Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning [0.0]
We argue that the challenge of algorithmic reasoning in question answering can be effectively tackled with a "systems" approach to AI. We propose an approach to algorithm reasoning for QA, Deep Algorithmic Question Answering.
arXiv Detail & Related papers (2021-09-16T14:28:18Z)
Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning [95.18337034090648]
We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG) These visual arithmetic problems are in the form of geometric figures. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
arXiv Detail & Related papers (2020-04-25T17:14:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.