{"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/genius-a-generalizable-and-purely","title":"Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning","arxiv_id":"2504.08672","date":"2025-04-11","proceeding":null,"authors":["Fangzhi Xu","Hang Yan","Chang Ma","Haiteng Zhao","Qiushi Sun","Kanzhi Cheng","Junxian He","Jun Liu","Zhiyong Wu"],"abstract":"Advancing LLM reasoning skills has captivated wide interest. However, current post-training techniques rely heavily on supervisory signals, such as outcome supervision or auxiliary reward models, which face the problem of scalability and high annotation costs. This motivates us to enhance LLM reasoning without the need for external supervision. We introduce a generalizable and purely unsupervised self-training framework, named Genius. Without external auxiliary, Genius requires to seek the optimal response sequence in a stepwise manner and optimize the LLM. To explore the potential steps and exploit the optimal ones, Genius introduces a stepwise foresight re-sampling strategy to sample and estimate the step value by simulating future outcomes. Further, we recognize that the unsupervised setting inevitably induces the intrinsic noise and uncertainty. To provide a robust optimization, we propose an advantage-calibrated optimization (ACO) loss function to mitigate estimation inconsistencies. Combining these techniques together, Genius provides an advanced initial step towards self-improve LLM reasoning with general queries and without supervision, revolutionizing reasoning scaling laws given the vast availability of general queries. The code will be released at https://github.com/xufangzhi/Genius.","url_abs":"https://arxiv.org/abs/2504.08672v1","url_pdf":"https://arxiv.org/pdf/2504.08672v1.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":"genius-a-generalizable-and-purely","repo_url":"https://github.com/xufangzhi/genius","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"genius-a-generalizable-and-purely","repo_url":"https://github.com/chang-github-00/llm-predictive-decoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.08672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08672"}},"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/chang-github-00/llm-predictive-decoding","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xufangzhi/genius","reach":null}],"summary":{"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":3,"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":4,"samples":[{"code_sha256_prefix":"2eb2d671ac2726a1","entry":"Registry","repo":"chang-github-00/llm-predictive-decoding","repo_kind":"listed","path":"agentboard/algorithms/mpc_sampling.py","file_url":"https://github.com/chang-github-00/llm-predictive-decoding/blob/HEAD/agentboard/algorithms/mpc_sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2eb2d671ac2726a1"}},{"code_sha256_prefix":"ef9600ec2720deb8","entry":"aco_loss","repo":"xufangzhi/genius","repo_kind":"official","path":"aco-training/open_instruct/aco_utils.py","file_url":"https://github.com/xufangzhi/genius/blob/HEAD/aco-training/open_instruct/aco_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef9600ec2720deb8"}},{"code_sha256_prefix":"94846e60d6f6c92a","entry":"count_tokens","repo":"chang-github-00/llm-predictive-decoding","repo_kind":"listed","path":"agentboard/algorithms/mpc_sampling.py","file_url":"https://github.com/chang-github-00/llm-predictive-decoding/blob/HEAD/agentboard/algorithms/mpc_sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94846e60d6f6c92a"}},{"code_sha256_prefix":"e87780fb396271cd","entry":"MPC_Sample","repo":"chang-github-00/llm-predictive-decoding","repo_kind":"listed","path":"agentboard/algorithms/mpc_sampling.py","file_url":"https://github.com/chang-github-00/llm-predictive-decoding/blob/HEAD/agentboard/algorithms/mpc_sampling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e87780fb396271cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}