{"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/thinkprune-pruning-long-chain-of-thought-of","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","arxiv_id":"2504.01296","date":"2025-04-02","proceeding":null,"authors":["Bairu Hou","Yang Zhang","Jiabao Ji","Yujian Liu","Kaizhi Qian","Jacob Andreas","Shiyu Chang"],"abstract":"We present ThinkPrune, a simple yet effective method for pruning the thinking length for long-thinking LLMs, which has been found to often produce inefficient and redundant thinking processes. Existing preliminary explorations of reducing thinking length primarily focus on forcing the thinking process to early exit, rather than adapting the LLM to optimize and consolidate the thinking process, and therefore the length-performance tradeoff observed so far is sub-optimal. To fill this gap, ThinkPrune offers a simple solution that continuously trains the long-thinking LLMs via reinforcement learning (RL) with an added token limit, beyond which any unfinished thoughts and answers will be discarded, resulting in a zero reward. To further preserve model performance, we introduce an iterative length pruning approach, where multiple rounds of RL are conducted, each with an increasingly more stringent token limit. We observed that ThinkPrune results in a remarkable performance-length tradeoff -- on the AIME24 dataset, the reasoning length of DeepSeek-R1-Distill-Qwen-1.5B can be reduced by half with only 2% drop in performance. We also observed that after pruning, the LLMs can bypass unnecessary steps while keeping the core reasoning process complete. Code is available at https://github.com/UCSB-NLP-Chang/ThinkPrune.","url_abs":"https://arxiv.org/abs/2504.01296v1","url_pdf":"https://arxiv.org/pdf/2504.01296v1.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":"thinkprune-pruning-long-chain-of-thought-of","repo_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.01296","atlas_url":"https://app.syntology.ai/?focus=2504.01296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01296"}},"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/UCSB-NLP-Chang/ThinkPrune","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_fixture":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":"242ecd8ee24f693b","entry":"convert_math","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/evaluation/data_utils.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/evaluation/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"242ecd8ee24f693b"}},{"code_sha256_prefix":"360c671d6041ba3b","entry":"create_huggingface_actor","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"360c671d6041ba3b"}},{"code_sha256_prefix":"42a7954a8cfa89e0","entry":"is_transformers_version_in_range","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/models/transformers/monkey_patch.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/models/transformers/monkey_patch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a7954a8cfa89e0"}},{"code_sha256_prefix":"21331a58f93375e4","entry":"union_tensor_dict","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/protocol.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/protocol.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"code_sha256_prefix":"25f0ea3f460f6ce1","entry":"unpad_dataproto","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/protocol.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25f0ea3f460f6ce1"}},{"code_sha256_prefix":"1fb4adb621eefddc","entry":"apply_monkey_patch","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/models/transformers/monkey_patch.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/models/transformers/monkey_patch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fb4adb621eefddc"}},{"code_sha256_prefix":"aaa4bac6dc85512a","entry":"call_api","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/evaluation/evalmath_main.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/evaluation/evalmath_main.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aaa4bac6dc85512a"}},{"code_sha256_prefix":"19472d4343d0a082","entry":"get_huggingface_actor_config","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19472d4343d0a082"}},{"code_sha256_prefix":"919cf310ad4c189a","entry":"get_weight_loader","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/models/weight_loader_registry.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"919cf310ad4c189a"}},{"code_sha256_prefix":"3b15e2ac7497c441","entry":"squeeze","repo":"UCSB-NLP-Chang/ThinkPrune","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/UCSB-NLP-Chang/ThinkPrune/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b15e2ac7497c441"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}