{"id":"https://openalex.org/W7208819344","doi":"https://doi.org/10.31223/x5tn59","title":"Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap","display_name":"Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap","publication_year":2026,"publication_date":"2026-09-05","ids":{"openalex":"https://openalex.org/W7208819344","doi":"https://doi.org/10.31223/x5tn59"},"language":"en","primary_location":{"id":"doi:10.31223/x5tn59","doi":"https://doi.org/10.31223/x5tn59","is_oa":true,"landing_page_url":"https://doi.org/10.31223/x5tn59","pdf_url":"https://eartharxiv.org/repository/object/14838/download/25791/","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eartharxiv.org/repository/object/14838/download/25791/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111288235","display_name":"Salah Alheejawi","orcid":"https://orcid.org/0000-0003-1949-6715","observed_orcids":["https://orcid.org/0000-0003-1949-6715"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"salah alheejawi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1949-6715","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002365998","display_name":"Valentas Gru\u017eauskas","orcid":"https://orcid.org/0000-0002-6997-9275","observed_orcids":["https://orcid.org/0000-0002-6997-9275"]},"institutions":[{"id":"https://openalex.org/I173212132","display_name":"Vilnius University","ror":"https://ror.org/03nadee84","country_code":"LT","type":"education","lineage":["https://openalex.org/I173212132"]}],"countries":["LT"],"is_corresponding":false,"raw_author_name":"Valentas Gruzauskas","raw_affiliation_strings":["Vilnius University , Lithuania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vilnius University , Lithuania","institution_ids":["https://openalex.org/I173212132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.19339999556541443,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.19339999556541443,"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"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.18129999935626984,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.04560000076889992,"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/llm-based-agents","display_name":"LLM agents","score":0.7710000276565552},{"id":"https://openalex.org/keywords/earth-observation","display_name":"Earth observation","score":0.824999988079071},{"id":"https://openalex.org/keywords/tool-orchestration","display_name":"tool orchestration","score":0.9620000123977661},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"remote sensing","score":0.5820000171661377},{"id":"https://openalex.org/keywords/foundation-model-adaptation","display_name":"foundation model adaptation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/evaluation-gap","display_name":"evaluation gap","score":0.6570000052452087},{"id":"https://openalex.org/keywords/agent-reliability","display_name":"agent reliability","score":0.574999988079071},{"id":"https://openalex.org/keywords/refusal-mechanisms","display_name":"refusal mechanisms","score":0.3540000021457672},{"id":"https://openalex.org/keywords/data-contracts","display_name":"data contracts","score":0.6110000014305115},{"id":"https://openalex.org/keywords/task-planning","display_name":"task planning","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084000110626221},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.703000009059906},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.6639999747276306},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6355999708175659},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4228000044822693},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4043999910354614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.31223/x5tn59","doi":"https://doi.org/10.31223/x5tn59","is_oa":true,"landing_page_url":"https://doi.org/10.31223/x5tn59","pdf_url":"https://eartharxiv.org/repository/object/14838/download/25791/","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:EA:id:14838","doi":null,"is_oa":true,"landing_page_url":"https://eartharxiv.org/repository/object/14838/download/25791/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402614","display_name":"EarthArXiv (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EarthArXiv","raw_type":"PREPRINTS"}],"best_oa_location":{"id":"doi:10.31223/x5tn59","doi":"https://doi.org/10.31223/x5tn59","is_oa":true,"landing_page_url":"https://doi.org/10.31223/x5tn59","pdf_url":"https://eartharxiv.org/repository/object/14838/download/25791/","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208819344.pdf","grobid_xml":"https://content.openalex.org/works/W7208819344.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4367365754","https://openalex.org/W4389720972","https://openalex.org/W4395055639","https://openalex.org/W4402916885","https://openalex.org/W4404782266","https://openalex.org/W4415332030","https://openalex.org/W4416034797","https://openalex.org/W4416613233","https://openalex.org/W4417127534","https://openalex.org/W7171800626"],"related_works":["https://openalex.org/W4415332030","https://openalex.org/W7127595130","https://openalex.org/W7212913219","https://openalex.org/W7157944994","https://openalex.org/W7222828286","https://openalex.org/W4402916885","https://openalex.org/W7152998594","https://openalex.org/W4416613233","https://openalex.org/W7221767154","https://openalex.org/W7204085365"],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"agents":[4,24,167],"have":[5,25],"moved":[6],"rapidly":[7],"from":[8,109,119],"general-purpose":[9],"assistants":[10],"to":[11,125,250],"domain":[12,235],"systems":[13],"that":[14,47,61,65,82,88,107,176,206,216],"orchestrate":[15],"specialised":[16],"remote-sensing":[17],"models.":[18],"Within":[19],"roughly":[20],"two":[21],"years,":[22],"geospatial":[23,55,203],"demonstrated":[26],"reliable":[27],"task":[28],"planning":[29],"across":[30],"dozens":[31],"of":[32,41],"Earth":[33],"Observation":[34],"(EO)":[35],"tasks,":[36],"benchmark":[37,134,158],"environments":[38],"containing":[39],"hundreds":[40],"tools,":[42],"and":[43,63,96,132,164,227,247],"fine-tuned":[44],"open-weight":[45],"controllers":[46],"outperform":[48],"far":[49],"larger":[50],"proprietary":[51],"models":[52,81,205],"at":[53],"generating":[54],"tool-use":[56],"chains.":[57],"This":[58],"review":[59],"synthesises":[60],"literature":[62],"argues":[64],"it":[66],"has":[67],"converged":[68],"on":[69,122,171],"a":[70,74,94,112,155,230],"common":[71,75],"architecture":[72,221],"with":[73],"limit.":[76],"Every":[77],"system":[78],"surveyed":[79],"orchestrates":[80],"human":[83,89,197],"researchers":[84],"built,":[85],"over":[86],"data":[87,152,242],"analysts":[90],"prepared;":[91],"none":[92,97],"designs":[93],"model,":[95],"constructs":[98],"its":[99],"own":[100],"analysis-ready":[101],"data.":[102],"We":[103,199],"identify":[104],"three":[105],"gaps":[106],"follow":[108],"this.":[110],"First,":[111],"reliability":[113],"wall:":[114],"reported":[115,190],"agent":[116],"success":[117],"falls":[118],"above":[120],"95%":[121],"single-tool":[123],"tasks":[124],"below":[126],"70%":[127],"beyond":[128],"eight":[129],"tool":[130],"calls,":[131],"scaling":[133],"volume":[135],"tenfold":[136],"does":[137],"not":[138],"expose":[139],"or":[140],"improve":[141],"this,":[142],"so":[143,166],"the":[144,172,201,209,223,248,256],"binding":[145],"variable":[146],"is":[147,188,222,253],"composition":[148],"depth":[149],"rather":[150,219,264],"than":[151,220,265],"quantity.":[153],"Second,":[154],"preprocessing":[156],"gap:":[157,184],"datasets":[159],"arrive":[160],"co-registered,":[161],"temporally":[162],"aligned":[163],"quality-flagged,":[165],"are":[168],"never":[169],"evaluated":[170],"multi-source":[173],"data-cube":[174],"construction":[175],"dominates":[177],"real":[178],"EO":[179,213],"practice.":[180],"Third,":[181],"an":[182],"evaluation":[183],"automated":[185],"LLM-as-judge":[186],"scoring":[187],"widely":[189],"as":[191,255],"ground":[192],"truth":[193],"without":[194],"calibration":[195],"against":[196],"experts.":[198],"survey":[200],"open":[202],"foundation":[204],"now":[207],"form":[208],"practical":[210],"substrate":[211],"for":[212],"modelling,":[214],"argue":[215],"adaptation":[217],"strategy":[218],"under-searched":[224],"design":[225],"variable,":[226],"set":[228],"out":[229],"research":[231],"agenda":[232],"in":[233],"which":[234,259],"constraint":[236],"\u2014":[237,252],"verified":[238],"templates,":[239],"physically":[240],"grounded":[241],"contracts,":[243],"explicit":[244],"compute":[245],"budgets":[246],"capacity":[249],"refuse":[251],"treated":[254],"mechanism":[257],"by":[258],"agentic":[260],"autonomy":[261],"becomes":[262],"verifiable":[263],"merely":[266],"fluent.":[267]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-06T00:00:00"}