{"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/open-reasoner-zero-an-open-source-approach-to","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","arxiv_id":"2503.24290","date":"2025-03-31","proceeding":null,"authors":["Jingcheng Hu","Yinmin Zhang","Qi Han","Daxin Jiang","Xiangyu Zhang","Heung-Yeung Shum"],"abstract":"We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training focusing on scalability, simplicity and accessibility. Through extensive experiments, we demonstrate that a minimalist approach, vanilla PPO with GAE ($\\lambda=1$, $\\gamma=1$) and straightforward rule-based rewards, without any KL regularization, is sufficient to scale up both response length and benchmark performance, similar to the phenomenon observed in DeepSeek-R1-Zero. Using the same base model as DeepSeek-R1-Zero-Qwen-32B, our implementation achieves superior performance on AIME2024, MATH500, and the GPQA Diamond benchmark while demonstrating remarkable efficiency -- requiring only a tenth of the training steps, compared to DeepSeek-R1-Zero pipeline. In the spirit of open source, we release our source code, parameter settings, training data, and model weights across various sizes.","url_abs":"https://arxiv.org/abs/2503.24290v1","url_pdf":"https://arxiv.org/pdf/2503.24290v1.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":"open-reasoner-zero-an-open-source-approach-to","repo_url":"https://github.com/open-reasoner-zero/open-reasoner-zero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.24290","atlas_url":"https://app.syntology.ai/?focus=2503.24290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.24290"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-reasoner-zero/open-reasoner-zero","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"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":"959df7824bf09cc1","entry":"log_probs_from_logits","repo":"open-reasoner-zero/open-reasoner-zero","repo_kind":"listed","path":"orz/ppo/models.py","file_url":"https://github.com/open-reasoner-zero/open-reasoner-zero/blob/HEAD/orz/ppo/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"959df7824bf09cc1"}},{"code_sha256_prefix":"c3b40f0f038248ce","entry":"repeatness","repo":"open-reasoner-zero/open-reasoner-zero","repo_kind":"listed","path":"playground/orz_14m_ppo_mini.py","file_url":"https://github.com/open-reasoner-zero/open-reasoner-zero/blob/HEAD/playground/orz_14m_ppo_mini.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3b40f0f038248ce"}},{"code_sha256_prefix":"71e6ee83ee6c4339","entry":"convert_ring_attn_params","repo":"open-reasoner-zero/open-reasoner-zero","repo_kind":"listed","path":"orz/ppo/models.py","file_url":"https://github.com/open-reasoner-zero/open-reasoner-zero/blob/HEAD/orz/ppo/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71e6ee83ee6c4339"}},{"code_sha256_prefix":"e93117d99aa6b210","entry":"reset_ring_attn_position_ids","repo":"open-reasoner-zero/open-reasoner-zero","repo_kind":"listed","path":"orz/ppo/models.py","file_url":"https://github.com/open-reasoner-zero/open-reasoner-zero/blob/HEAD/orz/ppo/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e93117d99aa6b210"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}