{"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/vtool-r1-vlms-learn-to-think-with-images-via","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","arxiv_id":"2505.19255","date":"2025-05-25","proceeding":null,"authors":["Mingyuan Wu","Jingcheng Yang","Jize Jiang","Meitang Li","Kaizhuo Yan","Hanchao Yu","Minjia Zhang","ChengXiang Zhai","Klara Nahrstedt"],"abstract":"Reinforcement Learning Finetuning (RFT) has significantly advanced the reasoning capabilities of large language models (LLMs) by enabling long chains of thought, self-correction, and effective tool use. While recent works attempt to extend RFT to vision-language models (VLMs), these efforts largely produce text-only reasoning conditioned on static image inputs, falling short of true multimodal reasoning in the response. In contrast, test-time methods like Visual Sketchpad incorporate visual steps but lack training mechanisms. We introduce VTool-R1, the first framework that trains VLMs to generate multimodal chains of thought by interleaving text and intermediate visual reasoning steps. VTool-R1 integrates Python-based visual editing tools into the RFT process, enabling VLMs to learn when and how to generate visual reasoning steps that benefit final reasoning. Trained with outcome-based rewards tied to task accuracy, our approach elicits strategic visual tool use for reasoning without relying on process-based supervision. Experiments on structured visual question answering over charts and tables show that VTool-R1 enhances reasoning performance by teaching VLMs to \"think with images\" and generate multimodal chain of thoughts with tools.","url_abs":"https://arxiv.org/abs/2505.19255v1","url_pdf":"https://arxiv.org/pdf/2505.19255v1.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":"vtool-r1-vlms-learn-to-think-with-images-via","repo_url":"https://github.com/VTOOL-R1/vtool-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.19255","atlas_url":"https://app.syntology.ai/?focus=2505.19255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19255"}},"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":"deterministic:regex_extraction","url":"https://github.com/VTOOL-R1/vtool-r1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"1104c28afa7dd8d2","entry":"encode_image","repo":"VTOOL-R1/vtool-r1","repo_kind":"listed","path":"eval/eval_gpt_no_tool.py","file_url":"https://github.com/VTOOL-R1/vtool-r1/blob/HEAD/eval/eval_gpt_no_tool.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1104c28afa7dd8d2"}},{"code_sha256_prefix":"67161499de84ab96","entry":"encode_image","repo":"VTOOL-R1/vtool-r1","repo_kind":"listed","path":"eval/eval_gpt_tableqa_with_tool.py","file_url":"https://github.com/VTOOL-R1/vtool-r1/blob/HEAD/eval/eval_gpt_tableqa_with_tool.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67161499de84ab96"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}