{"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/gpg-a-simple-and-strong-reinforcement","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","arxiv_id":"2504.02546","date":"2025-04-03","proceeding":null,"authors":["Xiangxiang Chu","Hailang Huang","Xiao Zhang","Fei Wei","Yong Wang"],"abstract":"Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and propose a minimalist RL approach termed Group Policy Gradient (GPG). Unlike conventional methods, GPG directly optimize the original RL objective, thus obviating the need for surrogate loss functions. By eliminating the critic and reference models, avoiding KL divergence constraints, and addressing the advantage and gradient estimation bias, our approach significantly simplifies the training process compared to Group Relative Policy Optimization (GRPO). Our approach achieves superior performance without relying on auxiliary techniques or adjustments. As illustrated in Figure 1, extensive experiments demonstrate that our method not only reduces computational costs but also consistently outperforms GRPO across various unimodal and multimodal tasks. Our code is available at https://github.com/AMAP-ML/GPG.","url_abs":"https://arxiv.org/abs/2504.02546v2","url_pdf":"https://arxiv.org/pdf/2504.02546v2.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":"gpg-a-simple-and-strong-reinforcement","repo_url":"https://github.com/amap-ml/gpg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2504.02546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02546"}},"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/amap-ml/gpg","reach":null}],"summary":{"ran_honours":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"039728581d8123a7","entry":"merge","repo":"amap-ml/gpg","repo_kind":"official","path":"open-r1/src/open_r1/gpg_trainer.py","file_url":"https://github.com/amap-ml/gpg/blob/HEAD/open-r1/src/open_r1/gpg_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"039728581d8123a7"}},{"code_sha256_prefix":"82e5778ec4883942","entry":"merge_with_padding","repo":"amap-ml/gpg","repo_kind":"official","path":"open-r1/src/open_r1/gpg_trainer.py","file_url":"https://github.com/amap-ml/gpg/blob/HEAD/open-r1/src/open_r1/gpg_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82e5778ec4883942"}},{"code_sha256_prefix":"f7cb83c9a6b015a3","entry":"pad_sequence_to_length","repo":"amap-ml/gpg","repo_kind":"official","path":"open-r1/src/open_r1/gpg_trainer.py","file_url":"https://github.com/amap-ml/gpg/blob/HEAD/open-r1/src/open_r1/gpg_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f7cb83c9a6b015a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}