{"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/vrest-enhancing-reasoning-in-large-vision","title":"VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism","arxiv_id":"2506.08691","date":"2025-06-10","proceeding":null,"authors":["Congzhi Zhang","Jiawei Peng","Zhenglin Wang","Yilong Lai","Haowen Sun","Heng Chang","Fei Ma","Weijiang Yu"],"abstract":"Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this paper, we propose VReST, a novel training-free approach that enhances Reasoning in LVLMs through Monte Carlo Tree Search and Self-Reward mechanisms. VReST meticulously traverses the reasoning landscape by establishing a search tree, where each node encapsulates a reasoning step, and each path delineates a comprehensive reasoning sequence. Our innovative multimodal Self-Reward mechanism assesses the quality of reasoning steps by integrating the utility of sub-questions, answer correctness, and the relevance of vision-language clues, all without the need for additional models. VReST surpasses current prompting methods and secures state-of-the-art performance across three multimodal mathematical reasoning benchmarks. Furthermore, it substantiates the efficacy of test-time scaling laws in multimodal tasks, offering a promising direction for future research.","url_abs":"https://arxiv.org/abs/2506.08691v1","url_pdf":"https://arxiv.org/pdf/2506.08691v1.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":"vrest-enhancing-reasoning-in-large-vision","repo_url":"https://github.com/garyjiajia/vrest","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.08691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08691"}},"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/garyjiajia/vrest","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/GaryJiajia/VReST","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":8,"ran_honours":3,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":15,"ran":12,"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":15,"samples":[{"code_sha256_prefix":"42a7905c3d9fae11","entry":"decompose_question_call","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42a7905c3d9fae11"}},{"code_sha256_prefix":"95e2fbff6927230d","entry":"default_call","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95e2fbff6927230d"}},{"code_sha256_prefix":"c2090c70720744a9","entry":"extract_final_answer","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2090c70720744a9"}},{"code_sha256_prefix":"70e61dd11bbbb998","entry":"extract_final_answer_word","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70e61dd11bbbb998"}},{"code_sha256_prefix":"e988a77dbfcbd745","entry":"extract_sub_questions_and_answers","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e988a77dbfcbd745"}},{"code_sha256_prefix":"35c7041f2e82cdd4","entry":"generate_message","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35c7041f2e82cdd4"}},{"code_sha256_prefix":"b12a0e6403b7a48c","entry":"get_reward_answer","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b12a0e6403b7a48c"}},{"code_sha256_prefix":"dfb51f6a8dac204c","entry":"get_reward_subquestion","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dfb51f6a8dac204c"}},{"code_sha256_prefix":"23ab440b8c99746d","entry":"is_terminal_question","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23ab440b8c99746d"}},{"code_sha256_prefix":"ade82f4c3e15e030","entry":"majority_vote","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ade82f4c3e15e030"}},{"code_sha256_prefix":"7b6d9846677a2001","entry":"reward_call","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b6d9846677a2001"}},{"code_sha256_prefix":"73dafb8d1befa5ba","entry":"simple_cot_call","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73dafb8d1befa5ba"}},{"code_sha256_prefix":"c78a0abbbc546ffb","entry":"get_reward","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c78a0abbbc546ffb"}},{"code_sha256_prefix":"71edd661f7ded9f1","entry":"get_reward_parallel","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71edd661f7ded9f1"}},{"code_sha256_prefix":"218cc9fda4a27e1f","entry":"our6_forward","repo":"GaryJiajia/VReST","repo_kind":"official","path":"prompt_methods/ours/our6.py","file_url":"https://github.com/GaryJiajia/VReST/blob/HEAD/prompt_methods/ours/our6.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"218cc9fda4a27e1f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}