{"id":"https://openalex.org/W7124149239","doi":"https://doi.org/10.48550/arxiv.2601.08699","title":"RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis","display_name":"RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis","publication_year":2026,"publication_date":"2026-01-13","ids":{"openalex":"https://openalex.org/W7124149239","doi":"https://doi.org/10.48550/arxiv.2601.08699"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.08699","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.08699","pdf_url":"https://arxiv.org/pdf/2601.08699","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.08699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108318794","display_name":"Zhengwei Tao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tao, Zhengwei","raw_affiliation_strings":["\u20dd Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151123282","display_name":"Bo Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Li, Bo","raw_affiliation_strings":["\u20dd Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133099868","display_name":"Jialong Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wu, Jialong","raw_affiliation_strings":["\u20dd Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122545445","display_name":"Guochen Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yan, Guochen","raw_affiliation_strings":["\u20dd Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026412038","display_name":"Huanyao Zhang","orcid":"https://orcid.org/0000-0003-2034-0355","observed_orcids":["https://orcid.org/0000-0003-2034-0355"]},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhang, Huanyao","raw_affiliation_strings":["\u20dd Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123047543","display_name":"Jiahao Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jiahao","raw_affiliation_strings":["\u20dd Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071533156","display_name":"Haitao Mi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mi, Haitao","raw_affiliation_strings":["\u20dd Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122994247","display_name":"Wentao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhang, Wentao","raw_affiliation_strings":["\u20dd Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u20dd Peking University ,","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.6782000064849854,"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":0.6782000064849854,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.2565999925136566,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.019500000402331352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/agentic-retrieval-augmented-generation","display_name":"agentic retrieval-augmented generation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.6320000290870667},{"id":"https://openalex.org/keywords/retrieval-failure","display_name":"retrieval failure","score":0.4519999921321869},{"id":"https://openalex.org/keywords/error-correction","display_name":"error correction","score":0.7440000176429749},{"id":"https://openalex.org/keywords/noise-rejection","display_name":"noise rejection","score":0.9359999895095825},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893000245094299},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6272000074386597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867000222206116},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.446399986743927},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C128913409","wikidata":"https://www.wikidata.org/wiki/Q3566063","display_name":"Belief revision","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.08699","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.08699","pdf_url":"https://arxiv.org/pdf/2601.08699","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.08699","doi":"https://doi.org/10.48550/arxiv.2601.08699","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.08699","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.08699","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.08699","pdf_url":"https://arxiv.org/pdf/2601.08699","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":null,"license_id":null,"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/W7124149239.pdf","grobid_xml":"https://content.openalex.org/works/W7124149239.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415332043","https://openalex.org/W4416220650","https://openalex.org/W7155451835","https://openalex.org/W7213400453","https://openalex.org/W7162044202","https://openalex.org/W4415926833","https://openalex.org/W4415282087","https://openalex.org/W7155070785","https://openalex.org/W7131817224","https://openalex.org/W4417356729"],"abstract_inverted_index":{"Agentic":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"empowers":[4],"large":[5],"language":[6],"models":[7,134],"to":[8,50,57,74,89,115],"autonomously":[9],"plan":[10],"and":[11,36,47,81,100,127,149],"retrieve":[12],"information":[13,92],"for":[14],"complex":[15,150],"problem-solving.":[16],"However,":[17],"the":[18,26,34,52,76],"development":[19],"of":[20,28,38,78],"robust":[21,82],"agents":[22],"is":[23,45],"hindered":[24],"by":[25],"scarcity":[27],"high-quality":[29],"training":[30],"data":[31,70],"that":[32,110,122,133],"reflects":[33],"noise":[35,128],"complexity":[37],"real-world":[39],"retrieval":[40,59,151],"environments.":[41],"Conventional":[42],"manual":[43],"annotation":[44],"unscalable":[46],"often":[48],"fails":[49],"capture":[51],"dynamic":[53],"reasoning":[54],"strategies":[55],"required":[56],"handle":[58],"failures.":[60],"To":[61],"bridge":[62],"this":[63],"gap,":[64],"we":[65,104],"introduce":[66],"RAGShaper,":[67],"a":[68,106,112],"novel":[69],"synthesis":[71],"framework":[72],"designed":[73],"automate":[75],"construction":[77],"RAG":[79],"tasks":[80],"agent":[83,114],"trajectories.":[84],"RAGShaper":[85],"incorporates":[86],"an":[87],"InfoCurator":[88],"build":[90],"dense":[91],"trees":[93],"enriched":[94],"with":[95],"adversarial":[96],"distractors":[97],"spanning":[98],"Perception":[99],"Cognition":[101],"levels.":[102],"Furthermore,":[103],"propose":[105],"constrained":[107],"navigation":[108],"strategy":[109],"forces":[111],"teacher":[113],"confront":[116],"these":[117],"distractors,":[118],"thereby":[119],"eliciting":[120],"trajectories":[121],"explicitly":[123],"demonstrate":[124],"error":[125],"correction":[126],"rejection.":[129],"Comprehensive":[130],"experiments":[131],"confirm":[132],"trained":[135],"on":[136],"our":[137],"synthesized":[138],"corpus":[139],"significantly":[140],"outperform":[141],"existing":[142],"baselines,":[143],"exhibiting":[144],"superior":[145],"robustness":[146],"in":[147],"noise-intensive":[148],"tasks.":[152]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-15T00:00:00"}