https://github.com/AIDC-AI/Marco-o1

\n","updatedAt":"2024-11-22T03:20:30.183Z","author":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","fullname":"AK","name":"akhaliq","type":"user","isPro":false,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":8213}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8434393405914307},"editors":["akhaliq"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg"],"reactions":[{"reaction":"🔥","users":["AdinaY"],"count":1}],"isReport":false}},{"id":"6740a00657c922e6aaa79eff","author":{"_id":"63a369d98c0c89dcae3b8329","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63a369d98c0c89dcae3b8329/AiH2zjy1cnt9OADAAZMLD.jpeg","fullname":"Adina Yakefu","name":"AdinaY","type":"user","isPro":true,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":1257},"createdAt":"2024-11-22T15:15:18.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Super cool! Congrats on the release🔥","html":"

Super cool! Congrats on the release🔥

\n","updatedAt":"2024-11-22T15:15:18.703Z","author":{"_id":"63a369d98c0c89dcae3b8329","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63a369d98c0c89dcae3b8329/AiH2zjy1cnt9OADAAZMLD.jpeg","fullname":"Adina Yakefu","name":"AdinaY","type":"user","isPro":true,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":1257}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7651758193969727},"editors":["AdinaY"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/63a369d98c0c89dcae3b8329/AiH2zjy1cnt9OADAAZMLD.jpeg"],"reactions":[],"isReport":false}},{"id":"674130e9230ab597786fb00c","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264},"createdAt":"2024-11-23T01:33:29.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://huggingface.co/papers/2410.09671) (2024)\n* [AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning](https://huggingface.co/papers/2411.11930) (2024)\n* [Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths](https://huggingface.co/papers/2410.10858) (2024)\n* [LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning](https://huggingface.co/papers/2410.02884) (2024)\n* [Interpretable Contrastive Monte Carlo Tree Search Reasoning](https://huggingface.co/papers/2410.01707) (2024)\n* [DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search](https://huggingface.co/papers/2410.03864) (2024)\n* [Rational Metareasoning for Large Language Models](https://huggingface.co/papers/2410.05563) (2024)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2024-11-23T01:33:29.183Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7297307252883911},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"6755f4bfa4b0a4a71a43080d","author":{"_id":"65f34e7cb4196c5a3b3cf2f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/UFCw8VDgq7v1EsI2M-TBM.jpeg","fullname":"Bikram Mondal","name":"notBik","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false},"createdAt":"2024-12-08T19:34:23.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Hey","html":"

Hey

\n","updatedAt":"2024-12-08T19:34:23.750Z","author":{"_id":"65f34e7cb4196c5a3b3cf2f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/UFCw8VDgq7v1EsI2M-TBM.jpeg","fullname":"Bikram Mondal","name":"notBik","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5519223213195801},"editors":["notBik"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/UFCw8VDgq7v1EsI2M-TBM.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2411.14405","authors":[{"_id":"673ff6ff60a79596d3e9aa99","name":"Yu Zhao","hidden":false},{"_id":"673ff6ff60a79596d3e9aa9a","name":"Huifeng Yin","hidden":false},{"_id":"673ff6ff60a79596d3e9aa9b","name":"Bo Zeng","hidden":false},{"_id":"673ff6ff60a79596d3e9aa9c","name":"Hao Wang","hidden":false},{"_id":"673ff6ff60a79596d3e9aa9d","user":{"_id":"66389e004ea0d8fe73853fea","avatarUrl":"/avatars/1b9bd9e64b9f3e2660f597ab65f3c15a.svg","isPro":false,"fullname":"ShiTianqi","user":"shitianqi","type":"user"},"name":"Tianqi Shi","status":"admin_assigned","statusLastChangedAt":"2024-11-22T13:06:18.643Z","hidden":false},{"_id":"673ff6ff60a79596d3e9aa9e","user":{"_id":"6527d8b077bceabaab382a75","avatarUrl":"/avatars/69caacf9153dbf6a3796693a968b363f.svg","isPro":false,"fullname":"Chenyang Lyu","user":"ChenyangLyu","type":"user"},"name":"Chenyang Lyu","status":"admin_assigned","statusLastChangedAt":"2024-11-22T13:06:07.311Z","hidden":false},{"_id":"673ff6ff60a79596d3e9aa9f","user":{"_id":"636b030c328133bdb3a523bc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/636b030c328133bdb3a523bc/f-OdbqqHiywkxQF1KVCLp.jpeg","isPro":false,"fullname":"Longyue Wang","user":"longyuewang","type":"user"},"name":"Longyue Wang","status":"admin_assigned","statusLastChangedAt":"2024-11-22T13:05:29.315Z","hidden":false},{"_id":"673ff6ff60a79596d3e9aaa0","user":{"_id":"66b03cedd59c09785e39711e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/N5yfQBSP3oAKPCz4ylR09.png","isPro":false,"fullname":"Weihua Luo","user":"acecamel1977","type":"user"},"name":"Weihua Luo","status":"admin_assigned","statusLastChangedAt":"2024-11-22T13:05:23.601Z","hidden":false},{"_id":"673ff6ff60a79596d3e9aaa1","user":{"_id":"63f87ebadf053017d1acbfdd","avatarUrl":"/avatars/e497ba5f41a2587837b4a6118d9367bb.svg","isPro":false,"fullname":"Kaifu Zhang","user":"zhangkaifu314","type":"user"},"name":"Kaifu Zhang","status":"admin_assigned","statusLastChangedAt":"2024-11-22T13:05:18.011Z","hidden":false}],"publishedAt":"2024-11-21T18:37:33.000Z","submittedOnDailyAt":"2024-11-22T00:50:30.177Z","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Currently OpenAI o1 has sparked a surge of interest in the study of large\nreasoning models (LRM). Building on this momentum, Marco-o1 not only focuses on\ndisciplines with standard answers, such as mathematics, physics, and coding --\nwhich are well-suited for reinforcement learning (RL) -- but also places\ngreater emphasis on open-ended resolutions. We aim to address the question:\n\"Can the o1 model effectively generalize to broader domains where clear\nstandards are absent and rewards are challenging to quantify?\" Marco-o1 is\npowered by Chain-of-Thought (CoT) fine-tuning, Monte Carlo Tree Search (MCTS),\nreflection mechanisms, and innovative reasoning strategies -- optimized for\ncomplex real-world problem-solving tasks.","upvotes":61,"discussionId":"673ff70060a79596d3e9ab4e","ai_summary":"Marco-o1 extends reasoning models to open-ended domains without clear standards using Chain-of-Thought fine-tuning, Monte Carlo Tree Search, reflection mechanisms, and innovative reasoning strategies.","ai_keywords":["Chain-of-Thought","Monte Carlo Tree Search","reflection mechanisms"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"65d9498780bafdfb4b218e77","avatarUrl":"/avatars/b5102ca17cd7d422584c5aaa8021bc86.svg","isPro":false,"fullname":"acg ","user":"lihua919","type":"user"},{"_id":"631a67b5c9f8cd19a736f6f2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/631a67b5c9f8cd19a736f6f2/nHFW6uUwOuCkLpjOPHSd9.jpeg","isPro":false,"fullname":"Fabio Dias Rollo","user":"fabiodr","type":"user"},{"_id":"6254f8e5d21e4cc386b881ad","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649899774659-6254f8e5d21e4cc386b881ad.jpeg","isPro":false,"fullname":"Somshubra Majumdar","user":"smajumdar94","type":"user"},{"_id":"65decc75beffeb39ba679eba","avatarUrl":"/avatars/735b678bd5863a0c1b1bdd3bbf8858fa.svg","isPro":true,"fullname":"r","user":"oceansweep","type":"user"},{"_id":"63082bb7bc0a2a5ee2253523","avatarUrl":"/avatars/6cf8d12d16d15db1070fbea89b5b3967.svg","isPro":false,"fullname":"Kuo-Hsin Tu","user":"dapumptu","type":"user"},{"_id":"5df82bcada6d0311fd3d5402","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1589104979708-5df82bcada6d0311fd3d5402.jpeg","isPro":false,"fullname":"Chuanming Liu","user":"Chuanming","type":"user"},{"_id":"63ddc7b80f6d2d6c3efe3600","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ddc7b80f6d2d6c3efe3600/RX5q9T80Jl3tn6z03ls0l.jpeg","isPro":false,"fullname":"J","user":"dashfunnydashdash","type":"user"},{"_id":"630430583926de1f7ec62c6b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/630430583926de1f7ec62c6b/mVQsL71KrGUs2H5hCTuO7.jpeg","isPro":true,"fullname":"Quan Nguyen","user":"qnguyen3","type":"user"},{"_id":"62b56eafa1bae3c711c208dd","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62b56eafa1bae3c711c208dd/f8ge3DFAvxNUItguemGuk.jpeg","isPro":false,"fullname":"Hieu Ngo","user":"hiieu","type":"user"},{"_id":"64d4615cf8082bf19b916492","avatarUrl":"/avatars/8e1b59565ec5e4b31090cf1b911781b9.svg","isPro":false,"fullname":"wongyukim","user":"wongyukim","type":"user"},{"_id":"64747f7e33192631bacd8831","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64747f7e33192631bacd8831/dstkZJ4sHJSeqLesV5cOC.jpeg","isPro":false,"fullname":"Taufiq Dwi Purnomo","user":"taufiqdp","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":2}">

Papers

arxiv:2411.14405

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

Published on Nov 21, 2024

· Submitted by

AK on Nov 22, 2024

#2 Paper of the day

Upvote

Authors:

Tianqi Shi ,

Chenyang Lyu ,

Longyue Wang ,

Weihua Luo ,

Kaifu Zhang

Abstract

Marco-o1 extends reasoning models to open-ended domains without clear standards using Chain-of-Thought fine-tuning, Monte Carlo Tree Search, reflection mechanisms, and innovative reasoning strategies.

AI-generated summary

Currently OpenAI o1 has sparked 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 arXiv page View PDF Add to collection