{"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/mm-react-prompting-chatgpt-for-multimodal","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","arxiv_id":"2303.11381","date":"2023-03-20","proceeding":null,"authors":["Zhengyuan Yang","Linjie Li","JianFeng Wang","Kevin Lin","Ehsan Azarnasab","Faisal Ahmed","Zicheng Liu","Ce Liu","Michael Zeng","Lijuan Wang"],"abstract":"We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows language models to accept, associate, and process multimodal information, thereby facilitating the synergetic combination of ChatGPT and various vision experts. Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding. Furthermore, we discuss and compare MM-REACT's system paradigm with an alternative approach that extends language models for multimodal scenarios through joint finetuning. Code, demo, video, and visualization are available at https://multimodal-react.github.io/","url_abs":"https://arxiv.org/abs/2303.11381v1","url_pdf":"https://arxiv.org/pdf/2303.11381v1.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":"mm-react-prompting-chatgpt-for-multimodal","repo_url":"https://github.com/microsoft/MM-REACT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"MM-ReAct-GPT-4","rank_in_archive_order":86,"of":231,"metrics":{"GPT-4 score":"44.6±0.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"MM-ReAct-GPT-3.5","rank_in_archive_order":215,"of":231,"metrics":{"GPT-4 score":"27.9±0.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.11381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11381"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/microsoft/MM-REACT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"344a8c239a10bbe4","entry":"get_color_mapping","repo":"microsoft/MM-REACT","repo_kind":"official","path":"langchain/input.py","file_url":"https://github.com/microsoft/MM-REACT/blob/HEAD/langchain/input.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":"344a8c239a10bbe4"}},{"code_sha256_prefix":"09a8bfab3c1ce96d","entry":"get_colored_text","repo":"microsoft/MM-REACT","repo_kind":"official","path":"langchain/input.py","file_url":"https://github.com/microsoft/MM-REACT/blob/HEAD/langchain/input.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":"09a8bfab3c1ce96d"}},{"code_sha256_prefix":"374d18fea1277220","entry":"get_entities","repo":"microsoft/MM-REACT","repo_kind":"official","path":"langchain/graphs/networkx_graph.py","file_url":"https://github.com/microsoft/MM-REACT/blob/HEAD/langchain/graphs/networkx_graph.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":"374d18fea1277220"}},{"code_sha256_prefix":"249d2034192505eb","entry":"parse_triples","repo":"microsoft/MM-REACT","repo_kind":"official","path":"langchain/graphs/networkx_graph.py","file_url":"https://github.com/microsoft/MM-REACT/blob/HEAD/langchain/graphs/networkx_graph.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":"249d2034192505eb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}