{"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/videorft-incentivizing-video-reasoning","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","arxiv_id":"2505.12434","date":"2025-05-18","proceeding":null,"authors":["Qi Wang","Yanrui Yu","Ye Yuan","Rui Mao","Tianfei Zhou"],"abstract":"Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental aspect of human intelligence, remains a persistent challenge due to the complex logic, temporal and causal structures inherent in video data. To fill this gap, we propose VIDEORFT, a novel approach that extends the RFT paradigm to cultivate human-like video reasoning capabilities in MLLMs. VIDEORFT follows the standard two-stage scheme in RFT: supervised fine-tuning (SFT) with chain-of-thought (CoT) annotations, followed by reinforcement learning (RL) to improve generalization. A central challenge to achieve this in the video domain lies in the scarcity of large-scale, high-quality video CoT datasets. We address this by building a fully automatic CoT curation pipeline. First, we devise a cognitioninspired prompting strategy to elicit a reasoning LLM to generate preliminary CoTs based solely on rich, structured, and literal representations of video content. Subsequently, these CoTs are revised by a visual-language model conditioned on the actual video, ensuring visual consistency and reducing visual hallucinations. This pipeline results in two new datasets - VideoRFT-CoT-102K for SFT and VideoRFT-RL-310K for RL. To further strength the RL phase, we introduce a novel semantic-consistency reward that explicitly promotes the alignment between textual reasoning with visual evidence. This reward encourages the model to produce coherent, context-aware reasoning outputs grounded in visual input. Extensive experiments show that VIDEORFT achieves state-of-the-art performance on six video reasoning benchmarks.","url_abs":"https://arxiv.org/abs/2505.12434v1","url_pdf":"https://arxiv.org/pdf/2505.12434v1.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":"videorft-incentivizing-video-reasoning","repo_url":"https://github.com/qiwang98/videorft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.12434","atlas_url":"https://app.syntology.ai/?focus=2505.12434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12434"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.12434"},"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":"2505.12434"},"call":"get_harvested_code_for_paper(arxiv_id=\"2505.12434\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2505.12434"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2505.12434\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2505.12434"},"call":"get_concepts_for_paper(arxiv_id=\"2505.12434\")"}],"by_repo":[{"repo":"qiwang98/videorft","kind":"official","samples":8,"ran":6,"instrument":0,"unverified":2}],"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","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/2505.12434.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/2505.12434.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/qiwang98/videorft","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_honours":4,"unverified":2},"n_samples":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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":8,"ran":6,"n_ran_checked":6,"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":2,"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":2,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"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":"d5ae7b1b53efaacf","code_sha256_prefix":"d5ae7b1b53efaacf","entry":"accuracy_reward","repo":"qiwang98/videorft","repo_kind":"official","path":"src/r1-v/src/open_r1/grpo.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/grpo.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"completions:list/1/list, solution:list/1/str, problem_type:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-25T00:28:05.031210+00:00","code_page":"/code/accuracy-reward","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d5ae7b1b53efaacf"}},{"code_sha256":"6e45201fa27cb24a","code_sha256_prefix":"6e45201fa27cb24a","entry":"ceil_by_factor","repo":"qiwang98/videorft","repo_kind":"official","path":"src/qwen-vl-utils/src/qwen_vl_utils/vision_process.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/qwen-vl-utils/src/qwen_vl_utils/vision_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"number:int/0/int, factor:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6e45201fa27cb24a"},"code_page":"/code/ceil-by-factor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6e45201fa27cb24a"}},{"code_sha256":"8155263d7ff19bb3","code_sha256_prefix":"8155263d7ff19bb3","entry":"floor_by_factor","repo":"qiwang98/videorft","repo_kind":"official","path":"src/qwen-vl-utils/src/qwen_vl_utils/vision_process.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/qwen-vl-utils/src/qwen_vl_utils/vision_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"number:int/0/int, factor:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8155263d7ff19bb3"},"code_page":"/code/floor-by-factor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8155263d7ff19bb3"}},{"code_sha256":"26720b6f9ee7eba4","code_sha256_prefix":"26720b6f9ee7eba4","entry":"format_reward","repo":"qiwang98/videorft","repo_kind":"official","path":"src/r1-v/src/open_r1/grpo.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/grpo.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"completions:list/1/list","fixture_out_type":"list","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","code_page":"/code/format-reward","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from zywang0104/Video-KTR, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"26720b6f9ee7eba4"}},{"code_sha256":"40640dbb4bed6b2c","code_sha256_prefix":"40640dbb4bed6b2c","entry":"prepare_dataset","repo":"qiwang98/videorft","repo_kind":"official","path":"src/r1-v/src/open_r1/sft_video.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/sft_video.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"example:dict/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-25T02:59:38.627214+00:00","code_page":"/code/prepare-dataset","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"40640dbb4bed6b2c"}},{"code_sha256":"e252767324188623","code_sha256_prefix":"e252767324188623","entry":"round_by_factor","repo":"qiwang98/videorft","repo_kind":"official","path":"src/qwen-vl-utils/src/qwen_vl_utils/vision_process.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/qwen-vl-utils/src/qwen_vl_utils/vision_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"number:int/0/int, factor:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"e252767324188623"},"code_page":"/code/round-by-factor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e252767324188623"}},{"code_sha256":"9de1d57aec154c7d","code_sha256_prefix":"9de1d57aec154c7d","entry":"download_video","repo":"qiwang98/videorft","repo_kind":"official","path":"src/r1-v/src/open_r1/sft_video.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/sft_video.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from zywang0104/Video-KTR, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"9de1d57aec154c7d"}},{"code_sha256":"82c65ef0ec85e093","code_sha256_prefix":"82c65ef0ec85e093","entry":"patched_load","repo":"qiwang98/videorft","repo_kind":"official","path":"src/r1-v/src/open_r1/grpo.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/grpo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"82c65ef0ec85e093"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d0876f6db2c68fb419165eb3dc8c97781e35b177936dd0e49886f5bd0ebf17ef","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}