{"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/agentic-r1-distilled-dual-strategy-reasoning","title":"Agentic-R1: Distilled Dual-Strategy Reasoning","arxiv_id":"2507.05707","date":"2025-07-08","proceeding":null,"authors":["Weihua Du","Pranjal Aggarwal","Sean Welleck","Yiming Yang"],"abstract":"Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, DualDistill, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train Agentic-R1, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems, and using text-based reasoning for abstract ones. Our method improves accuracy across a range of tasks, including both computation-intensive and standard benchmarks, demonstrating the effectiveness of multi-strategy distillation in achieving robust and efficient reasoning. Our project is available at https://github.com/StigLidu/DualDistill","url_abs":"https://arxiv.org/abs/2507.05707v1","url_pdf":"https://arxiv.org/pdf/2507.05707v1.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":[],"tasks":[{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2507.05707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.05707"}},"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/StigLidu/DualDistill","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"found_in_text":{"samples":7,"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":"bd6d9646398c3bd1","entry":"check_format","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"math_utils/format_checking.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/math_utils/format_checking.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd6d9646398c3bd1"}},{"code_sha256_prefix":"536565c77dd104b3","entry":"chunks_to_text","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"sft/evaluate.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/sft/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"536565c77dd104b3"}},{"code_sha256_prefix":"8840d612d6993c12","entry":"code_block","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"math_utils/utils.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/math_utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8840d612d6993c12"}},{"code_sha256_prefix":"34f7ef3ec0e38d89","entry":"find_answer","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"math_utils/utils.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/math_utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"34f7ef3ec0e38d89"}},{"code_sha256_prefix":"369084008556b156","entry":"find_nth","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"sft/dataloader.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/sft/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"369084008556b156"}},{"code_sha256_prefix":"196b62ea411c6575","entry":"find_question","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"math_utils/utils.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/math_utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"196b62ea411c6575"}},{"code_sha256_prefix":"7049441c97095c5e","entry":"get_token_length","repo":"StigLidu/DualDistill","repo_kind":"found_in_text","path":"sft/evaluate.py","file_url":"https://github.com/StigLidu/DualDistill/blob/HEAD/sft/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7049441c97095c5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}