{"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/limopro-reasoning-refinement-for-efficient","title":"LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling","arxiv_id":"2505.19187","date":"2025-05-25","proceeding":null,"authors":["Yang Xiao","Jiashuo Wang","Ruifeng Yuan","Chunpu Xu","Kaishuai Xu","Wenjie Li","PengFei Liu"],"abstract":"Large language models (LLMs) have demonstrated remarkable reasoning capabilities through test-time scaling approaches, particularly when fine-tuned with chain-of-thought (CoT) data distilled from more powerful large reasoning models (LRMs). However, these reasoning chains often contain verbose elements that mirror human problem-solving, categorized as progressive reasoning (the essential solution development path) and functional elements (verification processes, alternative solution approaches, and error corrections). While progressive reasoning is crucial, the functional elements significantly increase computational demands during test-time inference. We introduce PIR (Perplexity-based Importance Refinement), a principled framework that quantitatively evaluates the importance of each reasoning step based on its impact on answer prediction confidence. PIR systematically identifies and selectively prunes only low-importance functional steps while preserving progressive reasoning components, creating optimized training data that maintains the integrity of the core solution path while reducing verbosity. Models fine-tuned on PIR-optimized data exhibit superior test-time scaling properties, generating more concise reasoning chains while achieving improved accuracy (+0.9\\% to +6.6\\%) with significantly reduced token usage (-3\\% to -41\\%) across challenging reasoning benchmarks (AIME, AMC, and GPQA Diamond). Our approach demonstrates strong generalizability across different model sizes, data sources, and token budgets, offering a practical solution for deploying reasoning-capable LLMs in scenarios where efficient test-time scaling, response time, and computational efficiency are valuable constraints.","url_abs":"https://arxiv.org/abs/2505.19187v1","url_pdf":"https://arxiv.org/pdf/2505.19187v1.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":"limopro-reasoning-refinement-for-efficient","repo_url":"https://github.com/gair-nlp/limopro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.19187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19187"}},"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/gair-nlp/limopro","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"43f0a2dd8746fe09","entry":"calculate_full_string_perplexity","repo":"gair-nlp/limopro","repo_kind":"official","path":"CIE/cie.py","file_url":"https://github.com/gair-nlp/limopro/blob/HEAD/CIE/cie.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":"43f0a2dd8746fe09"}},{"code_sha256_prefix":"0350366c7fd8da6f","entry":"calculate_substring_perplexity","repo":"gair-nlp/limopro","repo_kind":"official","path":"CIE/cie.py","file_url":"https://github.com/gair-nlp/limopro/blob/HEAD/CIE/cie.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":"0350366c7fd8da6f"}},{"code_sha256_prefix":"aef09f6dd0e5a41c","entry":"find_substring_token_indices","repo":"gair-nlp/limopro","repo_kind":"official","path":"CIE/cie.py","file_url":"https://github.com/gair-nlp/limopro/blob/HEAD/CIE/cie.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":"aef09f6dd0e5a41c"}},{"code_sha256_prefix":"c3e7d16c56e40b3b","entry":"parse_model_output","repo":"gair-nlp/limopro","repo_kind":"official","path":"eval_/model_eval.py","file_url":"https://github.com/gair-nlp/limopro/blob/HEAD/eval_/model_eval.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":"c3e7d16c56e40b3b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}