{"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/light-r1-curriculum-sft-dpo-and-rl-for-long","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","arxiv_id":"2503.10460","date":"2025-03-13","proceeding":null,"authors":["Liang Wen","Yunke Cai","Fenrui Xiao","Xin He","Qi An","Zhenyu Duan","Yimin Du","Junchen Liu","Lifu Tang","Xiaowei Lv","Haosheng Zou","Yongchao Deng","Shousheng Jia","Xiangzheng Zhang"],"abstract":"This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning. Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPO on long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among 14B models in math, with AIME24 \\& 25 scores of 74.0 and 60.2 respectively, surpassing many 32B models and DeepSeek-R1-Distill-Llama-70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significant advancement in making sophisticated reasoning models more accessible and implementable in real-world applications. Our models, training data and code have been made available at https://github.com/Qihoo360/Light-R1.","url_abs":"https://arxiv.org/abs/2503.10460v3","url_pdf":"https://arxiv.org/pdf/2503.10460v3.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":"light-r1-curriculum-sft-dpo-and-rl-for-long","repo_url":"https://github.com/qihoo360/light-r1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.10460","atlas_url":"https://app.syntology.ai/?focus=2503.10460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10460"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.10460"},"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":"2503.10460"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.10460\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2503.10460"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2503.10460\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2503.10460"},"call":"get_concepts_for_paper(arxiv_id=\"2503.10460\")"}],"by_repo":[{"repo":"qihoo360/light-r1","kind":"official","samples":13,"ran":10,"instrument":4,"unverified":3}],"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/2503.10460.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/2503.10460.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/qihoo360/light-r1","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Qihoo360/Light-R1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":3,"ran_violates":1,"unverified":3},"n_samples":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"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":13,"ran":10,"n_ran_checked":6,"n_instrument":4,"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,"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,"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":10,"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":"57f0335f22430956","code_sha256_prefix":"57f0335f22430956","entry":"build_ngram_lookup","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"decontaminate/n_gram_check.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/decontaminate/n_gram_check.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"documents:list/1/str, ngram_size:int/0/int","fixture_out_type":"defaultdict","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"57f0335f22430956"}},{"code_sha256":"61619ba901c7b574","code_sha256_prefix":"61619ba901c7b574","entry":"clean_text","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"decontaminate/character_matching.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/decontaminate/character_matching.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","retrieve_with":{"tool":"get_code","code_sha256":"61619ba901c7b574"},"code_page":"/code/clean-text","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"61619ba901c7b574"}},{"code_sha256":"368d3db6347269c3","code_sha256_prefix":"368d3db6347269c3","entry":"count_unknown_letters_in_expr","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/deepscaler/rewards/math_utils/utils.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/deepscaler/rewards/math_utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"expr:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"368d3db6347269c3"},"code_page":"/code/count-unknown-letters-in-expr","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"368d3db6347269c3"}},{"code_sha256":"360c671d6041ba3b","code_sha256_prefix":"360c671d6041ba3b","entry":"create_huggingface_actor","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/verl/verl/utils/model.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/utils/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_name:str/0/str, override_config_kwargs:dict/0/?, automodel_kwargs:dict/0/?","fixture_out_type":"MockCausalLMModel","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/create-huggingface-actor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"code_sha256":"ec578739f88adc22","code_sha256_prefix":"ec578739f88adc22","entry":"mathd_normalize_answer","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/deepscaler/rewards/math_utils/utils.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/deepscaler/rewards/math_utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"answer:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-26T03:58:20.443611+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ec578739f88adc22"},"code_page":"/code/mathd-normalize-answer","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"code_sha256":"927fae1304011f13","code_sha256_prefix":"927fae1304011f13","entry":"normalize_string","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"decontaminate/n_gram_check.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/decontaminate/n_gram_check.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","retrieve_with":{"tool":"get_code","code_sha256":"927fae1304011f13"},"code_page":"/code/normalize-string","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"927fae1304011f13"}},{"code_sha256":"95f02454eddf082a","code_sha256_prefix":"95f02454eddf082a","entry":"should_allow_eval","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/deepscaler/rewards/math_utils/utils.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/deepscaler/rewards/math_utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"expr:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/should-allow-eval","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95f02454eddf082a"}},{"code_sha256":"21331a58f93375e4","code_sha256_prefix":"21331a58f93375e4","entry":"union_tensor_dict","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/verl/verl/protocol.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/protocol.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"tensor_dict1:TensorDict/1/float, tensor_dict2:TensorDict/1/float","fixture_out_type":"TensorDict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/union-tensor-dict","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"code_sha256":"25f0ea3f460f6ce1","code_sha256_prefix":"25f0ea3f460f6ce1","entry":"unpad_dataproto","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/verl/verl/protocol.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/protocol.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"data:DataProto/0/?, pad_size:int/0/int","fixture_out_type":"DataProto","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/unpad-dataproto","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"25f0ea3f460f6ce1"}},{"code_sha256":"b740be8e99a575cb","code_sha256_prefix":"b740be8e99a575cb","entry":"word_ngrams","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"decontaminate/n_gram_check.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/decontaminate/n_gram_check.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str, n:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b740be8e99a575cb"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b740be8e99a575cb"}},{"code_sha256":"19472d4343d0a082","code_sha256_prefix":"19472d4343d0a082","entry":"get_huggingface_actor_config","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/verl/verl/utils/model.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/utils/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-huggingface-actor-config","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"19472d4343d0a082"}},{"code_sha256":"919cf310ad4c189a","code_sha256_prefix":"919cf310ad4c189a","entry":"get_weight_loader","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/verl/verl/models/weight_loader_registry.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/models/weight_loader_registry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-weight-loader","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"919cf310ad4c189a"}},{"code_sha256":"3b15e2ac7497c441","code_sha256_prefix":"3b15e2ac7497c441","entry":"squeeze","repo":"Qihoo360/Light-R1","repo_kind":"official","path":"deepscaler-release/verl/verl/utils/model.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/verl/verl/utils/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/squeeze","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3b15e2ac7497c441"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1a77e5b94e8c70b25e3443ac977b1541503a6522a0b3d08613422d9b8ffb7592","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}