{"id":"https://openalex.org/W7141202608","doi":"https://doi.org/10.48550/arxiv.2603.25063","title":"TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization","display_name":"TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141202608","doi":"https://doi.org/10.48550/arxiv.2603.25063"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25063","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.2603.25063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116357976","display_name":"Nathaniel Gorski","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gorski, Nathaniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130737051","display_name":"Shusen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shusen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130740363","display_name":"Bei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5116357976"],"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9251000285148621,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9251000285148621,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.03999999910593033,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.729200005531311},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7200000286102295},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.7121000289916992},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.46299999952316284},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.39640000462532043},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.38179999589920044},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481000065803528},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.729200005531311},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7200000286102295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7121000289916992},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40950000286102295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.39640000462532043},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.375},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.34150001406669617},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25063","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.2603.25063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25063","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"agentic":[1,74],"systems":[2,21],"demonstrate":[3],"that":[4],"large":[5],"language":[6],"models":[7],"can":[8],"generate":[9],"scientific":[10,79],"visualizations":[11],"from":[12],"natural":[13],"language.":[14],"However,":[15],"reliability":[16,57],"remains":[17,63],"a":[18,70,103,118,136,194,222],"major":[19],"limitation:":[20],"may":[22],"execute":[23],"invalid":[24],"operations,":[25],"introduce":[26,193],"subtle":[27],"but":[28],"consequential":[29],"errors,":[30],"or":[31],"fail":[32],"to":[33,89,111,143,228],"request":[34],"missing":[35],"information":[36],"when":[37],"inputs":[38],"are":[39,43],"underspecified.":[40],"These":[41],"issues":[42],"amplified":[44],"in":[45,58],"real-world":[46],"workflows,":[47],"which":[48],"often":[49],"exceed":[50],"the":[51,107,185],"complexity":[52],"of":[53,131,153,177,196],"standard":[54],"benchmarks.":[55],"Ensuring":[56],"autonomous":[59],"visualization":[60,80,101,114],"pipelines":[61],"therefore":[62],"an":[64],"open":[65],"challenge.":[66],"We":[67],"present":[68],"TopoPilot,":[69],"reliable":[71,91],"and":[72,86,100,148,155,160,173,180,199,217,236],"extensible":[73],"framework":[75,108],"for":[76,203,231],"automating":[77],"complex":[78],"workflows.":[81],"TopoPilot":[82,116,220],"incorporates":[83],"systematic":[84],"guardrails":[85,235],"verification":[87,156],"mechanisms":[88],"ensure":[90],"operation.":[92],"While":[93],"we":[94,192],"focus":[95],"on":[96],"topological":[97],"data":[98],"analysis":[99],"as":[102],"primary":[104],"use":[105],"case,":[106],"is":[109],"designed":[110],"generalize":[112],"across":[113,212],"domains.":[115],"adopts":[117],"reliability-centered":[119],"two-agent":[120],"architecture.":[121],"An":[122],"orchestrator":[123],"agent":[124,138],"translates":[125],"user":[126],"prompts":[127],"into":[128],"workflows":[129,141,182],"composed":[130],"atomic":[132],"backend":[133],"actions,":[134],"while":[135],"verifier":[137],"evaluates":[139],"these":[140],"prior":[142],"execution,":[144],"enforcing":[145],"structural":[146],"validity":[147],"semantic":[149],"consistency.":[150],"This":[151],"separation":[152],"interpretation":[154],"reduces":[157],"code-generation":[158],"errors":[159],"enforces":[161],"correctness":[162],"guarantees.":[163],"A":[164],"modular":[165],"architecture":[166],"further":[167],"improves":[168],"robustness":[169],"by":[170],"isolating":[171],"components":[172],"enabling":[174],"seamless":[175],"integration":[176],"new":[178],"descriptors":[179],"domain-specific":[181],"without":[183,233],"modifying":[184],"core":[186],"system.":[187],"To":[188],"systematically":[189],"address":[190],"reliability,":[191],"taxonomy":[195],"failure":[197],"modes":[198],"implement":[200],"targeted":[201],"safeguards":[202],"each":[204],"class.":[205],"In":[206],"evaluations":[207],"simulating":[208],"1,000":[209],"multi-turn":[210],"conversations":[211],"100":[213],"prompts,":[214],"including":[215],"adversarial":[216],"infeasible":[218],"requests,":[219],"achieves":[221],"success":[223],"rate":[224],"exceeding":[225],"99%,":[226],"compared":[227],"under":[229],"50%":[230],"baselines":[232],"comprehensive":[234],"checks.":[237]},"counts_by_year":[],"updated_date":"2026-03-28T06:16:51.555046","created_date":"2026-03-28T00:00:00"}
