{"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/adaptivestep-automatically-dividing-reasoning","title":"AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence","arxiv_id":"2502.13943","date":"2025-02-19","proceeding":null,"authors":["Yuliang Liu","Junjie Lu","Zhaoling Chen","Chaofeng Qu","Jason Klein Liu","Chonghan Liu","Zefan Cai","Yunhui Xia","Li Zhao","Jiang Bian","Chuheng Zhang","Wei Shen","Zhouhan Lin"],"abstract":"Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size. These approaches overlook the fact that specific words do not typically mark true decision points in a text. To address this, we propose AdaptiveStep, a method that divides reasoning steps based on the model's confidence in predicting the next word. This division method provides more decision-making information at each step, enhancing downstream tasks, such as reward model learning. Moreover, our method does not require manual annotation. We demonstrate its effectiveness through experiments with AdaptiveStep-trained PRMs in mathematical reasoning and code generation tasks. Experimental results indicate that the outcome PRM achieves state-of-the-art Best-of-N performance, surpassing greedy search strategy with token-level value-guided decoding, while also reducing construction costs by over 30% compared to existing open-source PRMs. In addition, we provide a thorough analysis and case study on the PRM's performance, transferability, and generalization capabilities.","url_abs":"https://arxiv.org/abs/2502.13943v1","url_pdf":"https://arxiv.org/pdf/2502.13943v1.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":"adaptivestep-automatically-dividing-reasoning","repo_url":"https://github.com/lux0926/asprm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.13943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13943"}},"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":"deterministic:regex_extraction","url":"https://github.com/Lux0926/ASPRM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lux0926/asprm","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":4,"ran":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":4,"samples":[{"code_sha256_prefix":"380cbae376e743e4","entry":"confidence_detection","repo":"lux0926/asprm","repo_kind":"official","path":"evaluation/code/TVD/detector.py","file_url":"https://github.com/lux0926/asprm/blob/HEAD/evaluation/code/TVD/detector.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"380cbae376e743e4"}},{"code_sha256_prefix":"d7926978e3cfa22e","entry":"python_extract","repo":"lux0926/asprm","repo_kind":"official","path":"evaluation/code/TVD/tvd_lcb.py","file_url":"https://github.com/lux0926/asprm/blob/HEAD/evaluation/code/TVD/tvd_lcb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7926978e3cfa22e"}},{"code_sha256_prefix":"62569752807c6bc6","entry":"read_jsonl","repo":"lux0926/asprm","repo_kind":"official","path":"evaluation/code/TVD/tvd_lcb.py","file_url":"https://github.com/lux0926/asprm/blob/HEAD/evaluation/code/TVD/tvd_lcb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"62569752807c6bc6"}},{"code_sha256_prefix":"a1a9545f89348999","entry":"refine_text","repo":"lux0926/asprm","repo_kind":"official","path":"evaluation/code/TVD/tvd_lcb.py","file_url":"https://github.com/lux0926/asprm/blob/HEAD/evaluation/code/TVD/tvd_lcb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a1a9545f89348999"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}