{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/mm-verify-enhancing-multimodal-reasoning-with","title":"MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification","arxiv_id":"2502.13383","date":"2025-02-19","proceeding":null,"authors":["Linzhuang Sun","Hao Liang","Jingxuan Wei","Bihui Yu","Tianpeng Li","Fan Yang","Zenan Zhou","Wentao Zhang"],"abstract":"According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we introduce MM-Verifier and MM-Reasoner to enhance multimodal reasoning through longer inference and more robust verification. First, we propose a two-step MM verification data synthesis method, which combines a simulation-based tree search with verification and uses rejection sampling to generate high-quality Chain-of-Thought (COT) data. This data is then used to fine-tune the verification model, MM-Verifier. Additionally, we present a more efficient method for synthesizing MMCOT data, bridging the gap between text-based and multimodal reasoning. The synthesized data is used to fine-tune MM-Reasoner. Our MM-Verifier outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. Moreover, MM-Reasoner demonstrates strong effectiveness and scalability, with performance improving as data size increases. Finally, our approach achieves strong performance when combining MM-Reasoner and MM-Verifier, reaching an accuracy of 65.3 on MathVista, surpassing GPT-4o (63.8) with 12 rollouts.","url_abs":"https://arxiv.org/abs/2502.13383v1","url_pdf":"https://arxiv.org/pdf/2502.13383v1.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-verify-enhancing-multimodal-reasoning-with","repo_url":"https://github.com/aurora-slz/mm-verify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.13383","atlas_url":"https://app.syntology.ai/?focus=2502.13383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13383"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.13383"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.13383"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.13383\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2502.13383"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.13383\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.13383"},"call":"get_concepts_for_paper(arxiv_id=\"2502.13383\")"}],"by_repo":[{"repo":"aurora-slz/mm-verify","kind":"official","samples":4,"ran":0,"instrument":0,"unverified":4}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"bb4991aaf628f690","source_kind":"harvested","method_name":"MM-Verifier","realizes_method":"MM-Verifier","graph_method":"MM-Verifier","realizes_severed":false,"claim":"The paper claims this code implements a multimodal reasoning verifier and reasoner using Monte Carlo Tree Search (MCTS) with reflection and verification mechanisms to enhance multi-round reasoning in large language models.","centrality":"contribution","entry":"MCTS","entry_sha256":"856c9aad637b0958","n_bricks":13,"bricks":[{"entry":"MCTS","code_sha256":"856c9aad637b0958","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"MCTS_search","code_sha256":"040a0e7f4b118e77","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"executeRound","code_sha256":"cdde1fa1001fca90","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"treeNode","code_sha256":"ca2e487758bc8d8b","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"back_propagate","code_sha256":"15d94bcdfc2d9d1b","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"expand","code_sha256":"b694a3efa9770e88","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"getBestChild","code_sha256":"fb7427c831c79168","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"greedyPolicy","code_sha256":"921b11d38034e3e8","role":"sampler","order":7,"level":0,"status":"unverified"},{"entry":"randomPolicy","code_sha256":"f2cd3cffcc558e0c","role":"sampler","order":8,"level":0,"status":"unverified"},{"entry":"selectNode","code_sha256":"88d52f64be6d8180","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"get_next_steps_expand","code_sha256":"4fd1ea2325d783a5","role":"helper","order":10,"level":0,"status":"unverified"},{"entry":"get_next_steps_roll","code_sha256":"91b601baaf0d2b44","role":"helper","order":11,"level":1,"status":"ran_draft_wrong"},{"entry":"isTerminal","code_sha256":"04c9e8ce083656fc","role":"helper","order":12,"level":1,"status":"ran_violates"}],"ran_individually":5,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":3,"ran_violates":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d4c195fc9c15","n_siblings":0,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"d4c195fc9c15","realizes_method":"MM-Verifier","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["bb4991aaf628f690"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2502.13383"},"call":"assembly(arxiv_id=\"2502.13383\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2502.13383.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2502.13383.svg"},"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/aurora-slz/mm-verify","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Aurora-slz/MM-Verify","reach":{"status":"ok"}}],"summary":{"unverified":4},"n_samples":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":4,"ran":0,"n_ran_checked":0,"n_instrument":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":4,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"856c9aad637b0958","code_sha256_prefix":"856c9aad637b0958","entry":"MCTS","repo":"Aurora-slz/MM-Verify","repo_kind":"official","path":"search/MCTS/mcts.py","file_url":"https://github.com/Aurora-slz/MM-Verify/blob/HEAD/search/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/mcts","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aurora-slz/MM-Verify when it was checked","mcp_get_code":{"code_sha256":"856c9aad637b0958"}},{"code_sha256":"040a0e7f4b118e77","code_sha256_prefix":"040a0e7f4b118e77","entry":"MCTS_search","repo":"Aurora-slz/MM-Verify","repo_kind":"official","path":"search/MCTS/mcts.py","file_url":"https://github.com/Aurora-slz/MM-Verify/blob/HEAD/search/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aurora-slz/MM-Verify when it was checked","mcp_get_code":{"code_sha256":"040a0e7f4b118e77"}},{"code_sha256":"cdde1fa1001fca90","code_sha256_prefix":"cdde1fa1001fca90","entry":"executeRound","repo":"Aurora-slz/MM-Verify","repo_kind":"official","path":"search/MCTS/mcts.py","file_url":"https://github.com/Aurora-slz/MM-Verify/blob/HEAD/search/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aurora-slz/MM-Verify when it was checked","mcp_get_code":{"code_sha256":"cdde1fa1001fca90"}},{"code_sha256":"b694a3efa9770e88","code_sha256_prefix":"b694a3efa9770e88","entry":"expand","repo":"Aurora-slz/MM-Verify","repo_kind":"official","path":"search/MCTS/mcts.py","file_url":"https://github.com/Aurora-slz/MM-Verify/blob/HEAD/search/MCTS/mcts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/expand","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Aurora-slz/MM-Verify when it was checked","mcp_get_code":{"code_sha256":"b694a3efa9770e88"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0e801174929fbda3e2ee9dd6f2a5b38f411e7e73d7f7e267873f5dd60f0070f2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}