{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mulberry-empowering-mllm-with-o1-like","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","arxiv_id":"2412.18319","date":"2024-12-24","proceeding":null,"authors":["Huanjin Yao","Jiaxing Huang","Wenhao Wu","Jingyi Zhang","Yibo Wang","Shunyu Liu","Yingjie Wang","Yuxin Song","Haocheng Feng","Li Shen","DaCheng Tao"],"abstract":"In this work, we aim to develop an MLLM that understands and solves questions by learning to create each intermediate step of the reasoning involved till the final answer. To this end, we propose Collective Monte Carlo Tree Search (CoMCTS), a new learning-to-reason method for MLLMs, which introduces the concept of collective learning into ``tree search'' for effective and efficient reasoning-path searching and learning. The core idea of CoMCTS is to leverage collective knowledge from multiple models to collaboratively conjecture, search and identify effective reasoning paths toward correct answers via four iterative operations including Expansion, Simulation and Error Positioning, Backpropagation, and Selection. Using CoMCTS, we construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question. With Mulberry-260k, we perform collective SFT to train our model, Mulberry, a series of MLLMs with o1-like step-by-step Reasoning and Reflection capabilities. Extensive experiments demonstrate the superiority of our proposed methods on various benchmarks. Code will be available at https://github.com/HJYao00/Mulberry","url_abs":"https://arxiv.org/abs/2412.18319v2","url_pdf":"https://arxiv.org/pdf/2412.18319v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mulberry-empowering-mllm-with-o1-like","repo_url":"https://github.com/hjyao00/mulberry","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mulberry-empowering-mllm-with-o1-like","repo_url":"https://github.com/phunterlau/paper_without_code/tree/main/examples/mulberry","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.18319","atlas_url":"https://app.syntology.ai/?focus=2412.18319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18319"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phunterlau/paper_without_code/tree/main/examples/mulberry","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hjyao00/mulberry","reach":{"status":"ok"}}],"summary":{"ran":11,"unverified":2},"by_repo_kind":{"listed":{"samples":13,"ran":11,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d878e7e7996abb1c","entry":"analyze_execution_results","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/code_executor.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/code_executor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d878e7e7996abb1c"}},{"code_sha256_prefix":"26a082825804b823","entry":"benchmark_algorithm","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"templates/algorithm.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/templates/algorithm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26a082825804b823"}},{"code_sha256_prefix":"123ddb8ddb4564c3","entry":"create_conda_environment","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/code_executor.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/code_executor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"123ddb8ddb4564c3"}},{"code_sha256_prefix":"fcc6f5537839fe58","entry":"download_pdf","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/pdf_downloader.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/pdf_downloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcc6f5537839fe58"}},{"code_sha256_prefix":"b20fc8d9642b452c","entry":"evaluate_model","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"output/workflow/2411.16905/generated_code.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/output/workflow/2411.16905/generated_code.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b20fc8d9642b452c"}},{"code_sha256_prefix":"2332c3f0e7d84ce3","entry":"extract_arxiv_id","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/pdf_downloader.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/pdf_downloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2332c3f0e7d84ce3"}},{"code_sha256_prefix":"5a2d755aeb05fd00","entry":"generate_random_array","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"templates/algorithm.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/templates/algorithm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a2d755aeb05fd00"}},{"code_sha256_prefix":"df4a5c0a256b2e14","entry":"generate_sample_data","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"output/workflow/2411.16905/generated_code.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/output/workflow/2411.16905/generated_code.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df4a5c0a256b2e14"}},{"code_sha256_prefix":"1f13628b7e50b55a","entry":"run_code_with_timeout","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/code_executor.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/code_executor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f13628b7e50b55a"}},{"code_sha256_prefix":"69d1f8af6cf4447f","entry":"setup_logger","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/code_generator.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/code_generator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69d1f8af6cf4447f"}},{"code_sha256_prefix":"8fc873cde1192ad2","entry":"train_model","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"output/workflow/2411.16905/generated_code.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/output/workflow/2411.16905/generated_code.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8fc873cde1192ad2"}},{"code_sha256_prefix":"bc9d69072ce82a1f","entry":"estimate_api_cost","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"paperwocode/code_generator.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/paperwocode/code_generator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc9d69072ce82a1f"}},{"code_sha256_prefix":"2195c959742abc0f","entry":"measure_execution_time","repo":"phunterlau/paper_without_code","repo_kind":"listed","path":"templates/algorithm.py","file_url":"https://github.com/phunterlau/paper_without_code/blob/HEAD/templates/algorithm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2195c959742abc0f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}