{"id":"https://openalex.org/W7165162076","doi":"https://doi.org/10.48550/arxiv.2606.19047","title":"RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents","display_name":"RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165162076","doi":"https://doi.org/10.48550/arxiv.2606.19047"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.19047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109637392","display_name":"Ruishan Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Ruishan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108096359","display_name":"S Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Siyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061810614","display_name":"Chenyi Zhuang","orcid":"https://orcid.org/0000-0003-1891-5666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Chenyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138919454","display_name":"Tao Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.24410000443458557,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.24410000443458557,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.09220000356435776,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07039999961853027,"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/pipeline","display_name":"Pipeline (software)","score":0.6798999905586243},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.6604999899864197},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5185999870300293},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48829999566078186},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4650999903678894},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.38679999113082886},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742900013923645},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6798999905586243},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.6604999899864197},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.19047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-turn":[0],"tool-use":[1],"RL":[2,95,193],"is":[3],"bottlenecked":[4],"by":[5,100],"the":[6,18,27,35,42,70,92,102,118,158],"rapid":[7],"depletion":[8],"of":[9,34,72,171],"informative":[10,73],"samples":[11,40,74],"in":[12,21,75,197],"static":[13,77],"datasets.":[14],"We":[15,79],"observe":[16],"that":[17,112,155],"gradient":[19],"signal":[20],"GRPO":[22],"concentrates":[23],"on":[24],"tasks":[25],"with":[26,157],"highest":[28],"rollout":[29],"reward":[30,104],"variance,":[31],"a":[32,76,107,145,151,179],"consequence":[33],"Popoviciu":[36],"upper":[37],"bound.":[38],"Consequently,":[39],"near":[41],"agent's":[43],"capability":[44],"boundary":[45,64,110,128],"--":[46,54],"where":[47],"successes":[48],"and":[49,97,141,149,165,189,194],"failures":[50],"are":[51],"roughly":[52,185],"balanced":[53],"contribute":[55],"disproportionately":[56],"large":[57],"policy":[58],"gradients.":[59],"As":[60],"training":[61,96,169],"progresses,":[62],"this":[63,88],"continuously":[65,125],"shifts,":[66],"which":[67],"gradually":[68],"depletes":[69],"pool":[71,170],"dataset.":[78],"propose":[80],"RODS":[81,90,174],"(Reward-driven":[82],"Online":[83],"Data":[84],"Synthesis)":[85],"to":[86,178],"resolve":[87],"depletion.":[89],"closes":[91],"loop":[93],"between":[94],"data":[98],"generation":[99],"repurposing":[101],"progress":[103],"variance":[105],"as":[106],"practical,":[108],"zero-cost":[109],"detector":[111],"requires":[113],"no":[114],"extra":[115],"inference":[116],"beyond":[117],"rollouts":[119],"already":[120],"computed":[121],"for":[122],"training.":[123],"It":[124],"identifies":[126],"such":[127],"samples,":[129,173],"synthesizes":[130],"new":[131],"multi-turn":[132],"variants":[133],"matching":[134],"their":[135],"structural":[136],"complexity":[137],"(e.g.,":[138],"API":[139],"topology":[140],"dependency":[142],"depth)":[143],"via":[144],"skill-aligned":[146],"resampling":[147],"pipeline,":[148],"manages":[150],"dynamic":[152],"replay":[153],"buffer":[154],"co-evolves":[156],"policy.":[159],"Starting":[160],"from":[161],"400":[162],"human":[163],"seeds":[164],"maintaining":[166],"an":[167],"active":[168],"~800":[172],"achieves":[175],"comparable":[176],"performance":[177],"17K-sample":[180],"offline":[181],"pipeline":[182],"while":[183],"requiring":[184],"20x":[186],"fewer":[187],"trajectories,":[188],"improves":[190],"over":[191],"fixed-data":[192],"environment":[195],"augmentation":[196],"our":[198],"controlled":[199],"setting.":[200]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-19T00:00:00"}