{"id":"https://openalex.org/W7157171255","doi":"https://doi.org/10.48550/arxiv.2604.24198","title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","display_name":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7157171255","doi":"https://doi.org/10.48550/arxiv.2604.24198"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24198","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.24198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113431592","display_name":"Zhisong Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiu, Zhisong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134760125","display_name":"Shuofei Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Shuofei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122955745","display_name":"Kewei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Kewei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134805850","display_name":"Yuqi Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yuqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134803509","display_name":"Lun Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Lun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134818460","display_name":"Ningyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ningyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134788142","display_name":"Huajun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Huajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113431592"],"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/T10028","display_name":"Topic Modeling","score":0.2881999909877777,"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":0.2881999909877777,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.08489999920129776,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08449999988079071,"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/process","display_name":"Process (computing)","score":0.6281999945640564},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5210000276565552},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5019000172615051},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4440000057220459},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4153999984264374},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.35670000314712524},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.352400004863739},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354999780654907},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5210000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189999938011169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.352400004863739},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C100980136","wikidata":"https://www.wikidata.org/wiki/Q4668956","display_name":"Malleability","level":4,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24198","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.24198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24198","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47670796513557434}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Process":[0],"Reward":[1],"Models":[2,16],"(PRMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8,27],"augmenting":[9],"the":[10,107,216],"reasoning":[11],"capabilities":[12],"of":[13,218],"Large":[14],"Language":[15],"(LLMs)":[17],"within":[18],"static":[19],"domains":[20],"such":[21],"as":[22,100],"mathematics.":[23],"However,":[24],"their":[25],"potential":[26],"dynamic":[28],"data":[29,50],"analysis":[30,51],"tasks":[31],"remains":[32],"underexplored.":[33],"In":[34],"this":[35,84],"work,":[36],"we":[37,86],"first":[38],"present":[39],"a":[40,89,121,137],"empirical":[41],"study":[42],"revealing":[43],"that":[44,62,96,126,160],"general-domain":[45],"PRMs":[46],"struggle":[47],"to":[48,56,109,140],"supervise":[49],"agents.":[52],"Specifically,":[53],"they":[54],"fail":[55],"detect":[57],"silent":[58,116],"errors,":[59,117],"logical":[60],"flaws":[61],"yield":[63],"incorrect":[64],"results":[65,158],"without":[66],"triggering":[67],"interpreter":[68],"exceptions,":[69],"and":[70,114,118,132,153,170,186,211],"erroneously":[71],"penalize":[72],"exploratory":[73],"actions,":[74],"mistaking":[75],"necessary":[76],"trial-and-error":[77],"exploration":[78],"for":[79,147],"grounding":[80,130],"failures.":[81],"To":[82],"bridge":[83],"gap,":[85],"introduce":[87],"DataPRM,":[88],"novel":[90],"environment-aware":[91],"generative":[92],"process":[93,219],"reward":[94,124,220],"model":[95],"(1)":[97],"can":[98],"serve":[99],"an":[101],"active":[102],"verifier,":[103],"autonomously":[104],"interacting":[105],"with":[106,178],"environment":[108],"probe":[110],"intermediate":[111],"execution":[112],"states":[113],"uncover":[115],"(2)":[119],"employs":[120],"reflection-aware":[122],"ternary":[123],"strategy":[125],"distinguishes":[127],"between":[128],"correctable":[129],"errors":[131],"irrecoverable":[133],"mistakes.":[134],"We":[135],"design":[136],"scalable":[138],"pipeline":[139],"construct":[141],"over":[142,204],"8K":[143],"high-quality":[144],"training":[145],"instances":[146],"DataPRM":[148,161,182,197],"via":[149],"diversity-driven":[150],"trajectory":[151],"generation":[152],"knowledge-augmented":[154],"step-level":[155],"annotation.":[156],"Experimental":[157],"demonstrate":[159],"improves":[162],"downstream":[163],"policy":[164],"LLMs":[165],"by":[166],"7.21%":[167],"on":[168,172,209,213],"ScienceAgentBench":[169],"11.28%":[171],"DABStep":[173],"using":[174],"Best-of-N":[175],"inference.":[176],"Notably,":[177],"only":[179],"4B":[180],"parameters,":[181],"outperforms":[183],"strong":[184],"baselines,":[185,206],"exhibits":[187],"robust":[188],"generalizability":[189],"across":[190],"diverse":[191],"Test-Time":[192],"Scaling":[193],"strategies.":[194],"Furthermore,":[195],"integrating":[196],"into":[198],"Reinforcement":[199],"Learning":[200],"yields":[201],"substantial":[202],"gains":[203],"outcome-reward":[205],"achieving":[207],"78.73%":[208],"DABench":[210],"64.84%":[212],"TableBench,":[214],"validating":[215],"effectiveness":[217],"supervision.":[221],"Code":[222],"is":[223],"available":[224],"at":[225],"https://github.com/zjunlp/DataMind.":[226]},"counts_by_year":[],"updated_date":"2026-04-29T06:16:36.941037","created_date":"2026-04-29T00:00:00"}