{"id":"https://openalex.org/W4416040332","doi":"https://doi.org/10.48550/arxiv.2503.10613","title":"CoSTA$\\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing","display_name":"CoSTA$\\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4416040332","doi":"https://doi.org/10.48550/arxiv.2503.10613"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.10613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10613","pdf_url":"https://arxiv.org/pdf/2503.10613","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101222292","display_name":"Advait Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gupta, Advait","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095768786","display_name":"NandaKiran Velaga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Velaga, NandaKiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nguyen, Dang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Dang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114310439","display_name":"Tianyi Zhou","orcid":"https://orcid.org/0009-0000-5620-9362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tianyi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101222292"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4950999915599823,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4950999915599823,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.227400004863739,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.02879999950528145,"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/workflow","display_name":"Workflow","score":0.751800000667572},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5939000248908997},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4814999997615814},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3628999888896942},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3490999937057495}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.751800000667572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257999777793884},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5939000248908997},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47940000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.10613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10613","pdf_url":"https://arxiv.org/pdf/2503.10613","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.10613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10613","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10613","pdf_url":"https://arxiv.org/pdf/2503.10613","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"models":[1,51,227],"like":[2],"stable":[3],"diffusion":[4],"and":[5,66,86,120,140,179,235,237],"DALLE-3":[6],"still":[7],"struggle":[8],"with":[9],"multi-turn":[10,218],"image":[11,219],"editing.":[12],"We":[13,94,211],"decompose":[14],"such":[15],"a":[16,28,96,105,111,131,164,169,207,213],"task":[17],"as":[18],"an":[19,173],"agentic":[20],"workflow":[21],"(path)":[22],"of":[23,30,35,56,64,68,83,113,146,175,216,232],"tool":[24,46,92,132,148],"use":[25],"that":[26,100],"addresses":[27],"sequence":[29],"subtasks":[31,205],"by":[32,163],"AI":[33,114],"tools":[34,69,115],"varying":[36],"costs.":[37],"Conventional":[38],"search":[39,88,124,187],"algorithms":[40],"require":[41],"expensive":[42],"exploration":[43],"to":[44,70,73,89,103,129,152,193],"find":[45,90,130],"paths.":[47,196],"While":[48],"large":[49],"language":[50],"(LLMs)":[52],"possess":[53],"prior":[54],"knowledge":[55],"subtask":[57,106,151],"planning,":[58],"they":[59],"may":[60],"lack":[61],"accurate":[62],"estimations":[63],"capabilities":[65],"costs":[67],"determine":[71],"which":[72,108,222],"apply":[74],"in":[75,230],"each":[76,147],"subtask.":[77,183],"Can":[78],"we":[79],"combine":[80],"the":[81,117,126,137,154,176,182,185],"strengths":[82],"both":[84,144,233],"LLMs":[85,102],"graph":[87,112],"cost-efficient":[91],"paths?":[93],"propose":[95],"three-stage":[97],"approach":[98],"\"CoSTA*\"":[99],"leverages":[101],"create":[104],"tree,":[107],"helps":[109],"prune":[110],"for":[116,206],"given":[118],"task,":[119],"then":[121,161],"conducts":[122],"A*":[123,155,186],"on":[125,149,181,221],"small":[127],"subgraph":[128],"path.":[133],"To":[134],"better":[135,208],"balance":[136],"total":[138],"cost":[139,178,234],"quality,":[141,236],"CoSTA*":[142,198,223],"combines":[143],"metrics":[145],"every":[150],"guide":[153],"search.":[156],"Each":[157],"subtask's":[158],"output":[159],"is":[160],"evaluated":[162],"vision-language":[165],"model":[166],"(VLM),":[167],"where":[168],"failure":[170],"will":[171],"trigger":[172],"update":[174],"tool's":[177],"quality":[180],"Hence,":[184],"can":[188,199],"recover":[189],"from":[190],"failures":[191],"quickly":[192],"explore":[194],"other":[195],"Moreover,":[197],"automatically":[200],"switch":[201],"between":[202],"modalities":[203],"across":[204],"cost-quality":[209],"trade-off.":[210],"build":[212],"novel":[214],"benchmark":[215],"challenging":[217],"editing,":[220],"outperforms":[224],"state-of-the-art":[225],"image-editing":[226],"or":[228],"agents":[229],"terms":[231],"performs":[238],"versatile":[239],"trade-offs":[240],"upon":[241],"user":[242],"preference.":[243]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}