{"id":"https://openalex.org/W7127578024","doi":"https://doi.org/10.48550/arxiv.2602.03279","title":"Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis","display_name":"Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127578024","doi":"https://doi.org/10.48550/arxiv.2602.03279"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.03279","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03279","pdf_url":"https://arxiv.org/pdf/2602.03279","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.03279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138132706","display_name":"Zhengbo Jiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Zhengbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125091725","display_name":"Shaobo Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shaobo","raw_affiliation_strings":["EPIC Lab , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124235807","display_name":"Zifan Zhang","orcid":"https://orcid.org/0009-0006-7596-9686","observed_orcids":["https://orcid.org/0009-0006-7596-9686"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zifan","raw_affiliation_strings":["Wuhan University * Project leader ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University * Project leader ,","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125090624","display_name":"Xuan Ren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Xuan","raw_affiliation_strings":["AI DATA , Alibaba Group Holding Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI DATA , Alibaba Group Holding Limited","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125005656","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0003-4377-5060","observed_orcids":["https://orcid.org/0000-0003-4377-5060"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":["AI DATA , Alibaba Group Holding Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI DATA , Alibaba Group Holding Limited","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125054862","display_name":"Bing Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Bing","raw_affiliation_strings":["AI DATA , Alibaba Group Holding Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI DATA , Alibaba Group Holding Limited","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124906862","display_name":"Hu Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Hu","raw_affiliation_strings":["AI DATA , Alibaba Group Holding Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI DATA , Alibaba Group Holding Limited","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124973202","display_name":"Linfeng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Linfeng","raw_affiliation_strings":["EPIC Lab , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPIC Lab , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5067999958992004,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5067999958992004,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.14730000495910645,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.059300001710653305,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-model-reasoning","display_name":"large language model reasoning","score":0.7549999952316284},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.6060000061988831},{"id":"https://openalex.org/keywords/multi-agent-reasoning","display_name":"multi-agent reasoning","score":0.4950000047683716},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.5450000166893005},{"id":"https://openalex.org/keywords/mathematical-problem-solving","display_name":"mathematical problem solving","score":0.7059999704360962},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016999959945679},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.612500011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622000098228455},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C3019612716","wikidata":"https://www.wikidata.org/wiki/Q730920","display_name":"Problem solver","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.03279","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03279","pdf_url":"https://arxiv.org/pdf/2602.03279","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.03279","doi":"https://doi.org/10.48550/arxiv.2602.03279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.03279","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.03279","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03279","pdf_url":"https://arxiv.org/pdf/2602.03279","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127578024.pdf","grobid_xml":"https://content.openalex.org/works/W7127578024.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4392822190","https://openalex.org/W6967058914"],"related_works":["https://openalex.org/W4416238186","https://openalex.org/W4415337198","https://openalex.org/W7083290863","https://openalex.org/W4416017259","https://openalex.org/W4412945228","https://openalex.org/W7140132769","https://openalex.org/W4412888300","https://openalex.org/W7197050206","https://openalex.org/W7202406069","https://openalex.org/W7139048291"],"abstract_inverted_index":{"Advancing":[0],"complex":[1],"reasoning":[2,77],"in":[3],"large":[4],"language":[5],"models":[6,59,147],"relies":[7],"on":[8,115,132,142],"high-quality,":[9],"verifiable":[10,100],"datasets,":[11],"yet":[12],"human":[13],"annotation":[14],"remains":[15],"cost-prohibitive":[16],"and":[17,74,86,106,122,151],"difficult":[18],"to":[19,39,44,97],"scale.":[20],"Current":[21],"synthesis":[22,61],"paradigms":[23],"often":[24],"face":[25],"a":[26,56,63,69,128,138,154],"recurring":[27],"trade-off:":[28],"maintaining":[29],"structural":[30],"validity":[31],"typically":[32],"restricts":[33],"problem":[34,60],"complexity,":[35],"while":[36],"relaxing":[37],"constraints":[38],"increase":[40],"difficulty":[41],"frequently":[42],"leads":[43],"inconsistent":[45],"or":[46],"unsolvable":[47],"instances.":[48],"To":[49],"address":[50],"this,":[51],"we":[52,88],"propose":[53],"Agentic":[54],"Proposing,":[55],"framework":[57],"that":[58,111,153],"as":[62,149],"goal-driven":[64],"sequential":[65],"decision":[66],"process":[67],"where":[68],"specialized":[70],"agent":[71],"dynamically":[72],"selects":[73],"composes":[75],"modular":[76],"skills.":[78],"Through":[79],"an":[80],"iterative":[81],"workflow":[82],"of":[83,157],"internal":[84],"reflection":[85],"tool-use,":[87],"develop":[89],"the":[90],"Agentic-Proposer-4B":[91],"using":[92],"Multi-Granularity":[93],"Policy":[94],"Optimization":[95],"(MGPO)":[96],"generate":[98],"high-precision,":[99],"training":[101],"trajectories":[102,136],"across":[103],"mathematics,":[104],"coding,":[105],"science.":[107],"Empirical":[108],"results":[109],"demonstrate":[110],"downstream":[112],"solvers":[113],"trained":[114,131],"agent-synthesized":[116],"data":[117],"significantly":[118],"outperform":[119],"leading":[120],"baselines":[121],"exhibit":[123],"robust":[124],"cross-domain":[125],"generalization.":[126],"Notably,":[127],"30B":[129],"solver":[130],"only":[133],"11,000":[134],"synthesized":[135],"achieves":[137],"state-of-the-art":[139],"91.6%":[140],"accuracy":[141],"AIME25,":[143],"rivaling":[144],"frontier-scale":[145],"proprietary":[146],"such":[148],"GPT-5":[150],"proving":[152],"small":[155],"volume":[156],"high-quality":[158],"synthetic":[159],"signals":[160],"can":[161],"effectively":[162],"substitute":[163],"for":[164],"massive":[165],"human-curated":[166],"datasets.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":14}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-06T00:00:00"}