Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang, Tianqi Shi +4 more
11/21/2024
cs.CL

No official code found. Best implementation: AIDC-AI/Marco-o1 (1,538 stars, last commit 2026-02-13).

Abstract

Currently OpenAI o1 sparks a surge of interest in the study of large reasoning models (LRM). Building on this momentum, Marco-o1 not only focuses on disciplines with standard answers, such as mathematics, physics, and coding -- which are well-suited for reinforcement learning (RL) -- but also places greater emphasis on open-ended resolutions. We aim to address the question: ''Can the o1 model effectively generalize to broader domains where clear standards are absent and rewards are challenging to quantify?'' Marco-o1 is powered by Chain-of-Thought (CoT) fine-tuning, Monte Carlo Tree Search (MCTS), reflection mechanisms, and innovative reasoning strategies -- optimized for complex real-world problem-solving tasks.

View on arXivView PDF

Code Implementations(1)

AIDC-AI/Marco-o1Community100%

An Open Large Reasoning Model for Real-World Solutions

1,53882HTML, ShellOct 22, 20248 months agoNOASSERTION

Cite this paper

@article{zhao2024marcoo,
  title  = {Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions},
  author = {Yu Zhao and Huifeng Yin and Bo Zeng and Hao Wang and Tianqi Shi and Chenyang Lyu and Longyue Wang and Weihua Luo and Kaifu Zhang},
  year   = {2024},
  eprint = {2411.14405},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.14405v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.14405.svg)](https://codeofpaper.com/paper/2411.14405)

Discussion