{"id":"https://openalex.org/W7204099037","doi":"https://doi.org/10.48550/arxiv.2608.20634","title":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","display_name":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204099037","doi":"https://doi.org/10.48550/arxiv.2608.20634"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20634","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20634","pdf_url":"https://arxiv.org/pdf/2608.20634","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20634","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007444423","display_name":"Minbyul Jeong","orcid":"https://orcid.org/0000-0002-1346-730X","observed_orcids":["https://orcid.org/0000-0002-1346-730X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeong, Minbyul","raw_affiliation_strings":["Energy Construction Technology Logistics Commodities Telecom Automotive","Meridian Intelligence Global Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Energy Construction Technology Logistics Commodities Telecom Automotive","institution_ids":[]},{"raw_affiliation_string":"Meridian Intelligence Global Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113395856","display_name":"Chanwoong Yoon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoon, Chanwoong","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"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":3,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8140000104904175,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8140000104904175,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.07460000365972519,"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":0.05339999869465828,"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/business-scenarios","display_name":"business scenarios","score":0.7049999833106995},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6520000100135803},{"id":"https://openalex.org/keywords/reinforcement-learning-agents","display_name":"reinforcement learning agents","score":0.41600000858306885},{"id":"https://openalex.org/keywords/business-workflows","display_name":"business workflows","score":0.5979999899864197},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.6330000162124634},{"id":"https://openalex.org/keywords/qwen3-5","display_name":"Qwen3.5","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8521000146865845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800599992275238},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7371000051498413},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.5627999901771545},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37310001254081726},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20634","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20634","pdf_url":"https://arxiv.org/pdf/2608.20634","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.20634","doi":"https://doi.org/10.48550/arxiv.2608.20634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20634","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.20634","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20634","pdf_url":"https://arxiv.org/pdf/2608.20634","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204099037.pdf","grobid_xml":"https://content.openalex.org/works/W7204099037.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2795843265","https://openalex.org/W2992977009","https://openalex.org/W4226227340","https://openalex.org/W4385474529","https://openalex.org/W4388926373","https://openalex.org/W4391631327","https://openalex.org/W4392781346","https://openalex.org/W4399836817","https://openalex.org/W4402671485","https://openalex.org/W4409049124","https://openalex.org/W4409147637","https://openalex.org/W4415252687","https://openalex.org/W4417136556","https://openalex.org/W7127367462","https://openalex.org/W7128641923","https://openalex.org/W7130402983","https://openalex.org/W7133596291","https://openalex.org/W7138308002","https://openalex.org/W7155090332","https://openalex.org/W7160095038","https://openalex.org/W7161717673","https://openalex.org/W7161983523","https://openalex.org/W7162778800","https://openalex.org/W7165632540","https://openalex.org/W7165749951","https://openalex.org/W7167815111","https://openalex.org/W7171552453","https://openalex.org/W7171566560"],"related_works":["https://openalex.org/W7161717673","https://openalex.org/W7123371588","https://openalex.org/W7128399534","https://openalex.org/W7212053155","https://openalex.org/W7223245140","https://openalex.org/W4416237351","https://openalex.org/W7128648738","https://openalex.org/W7223027552","https://openalex.org/W4415196747","https://openalex.org/W7155090332"],"abstract_inverted_index":{"Agents":[0],"learn":[1],"to":[2,31,156,163,194],"act":[3],"through":[4],"interaction":[5,93],"with":[6,79],"environments,":[7],"yet":[8],"the":[9,47,123,176],"environments":[10,33,59,102,131,205],"used":[11],"for":[12,56,69,115],"training":[13,113,168],"are":[14],"often":[15],"manually":[16],"constructed":[17],"or":[18],"synthesized":[19],"around":[20],"predefined":[21],"tasks":[22,42,91],"and":[23,37,84,92,106,109,138,146,160,209],"benchmarks.":[24],"This":[25],"task-centric":[26],"paradigm":[27],"makes":[28],"it":[29],"difficult":[30],"scale":[32],"that":[34,175,203],"reflect":[35],"realistic":[36],"evolving":[38],"workflows":[39,137],"where":[40],"diverse":[41,90],"can":[43,95,180,206,219],"naturally":[44],"emerge":[45],"from":[46,60,88,154,161,192],"underlying":[48],"world.":[49],"We":[50,98,172],"introduce":[51],"AgentMercury,":[52],"a":[53,70,76,222],"scalable":[54],"framework":[55],"synthesizing":[57],"executable":[58,85,101],"high-level":[61],"business":[62,198],"scenarios.":[63,199],"Rather":[64],"than":[65],"constructing":[66],"an":[67],"environment":[68],"specific":[71],"task,":[72],"AgentMercury":[73,170],"first":[74],"instantiates":[75],"persistent":[77],"world":[78],"entities,":[80],"services,":[81],"tools,":[82],"state,":[83],"cross-service":[86],"invariants,":[87],"which":[89],"trajectories":[94],"subsequently":[96],"emerge.":[97],"construct":[99],"4,783":[100],"spanning":[103,141],"14":[104],"industries":[105],"50":[107],"countries,":[108],"use":[110],"them":[111],"as":[112],"substrates":[114],"reinforcement":[116],"learning.":[117],"Despite":[118],"being":[119],"generated":[120],"without":[121],"targeting":[122],"evaluation":[124],"benchmarks,":[125],"policies":[126],"trained":[127],"on":[128,134,158,165,169,185,196],"these":[129],"business-oriented":[130],"improve":[132],"substantially":[133],"both":[135],"enterprise":[136],"out-of-domain":[139],"benchmarks":[140],"reasoning,":[142],"coding,":[143],"scientific":[144],"computing,":[145],"tool":[147],"use.":[148],"In":[149],"our":[150],"experiments,":[151],"Qwen3.5-4B":[152],"improves":[153],"12.3":[155],"15.7":[157],"EnterpriseOps-GYM":[159],"45.9":[162],"56.0":[164],"AIME26":[166],"after":[167],"environments.":[171],"further":[173],"show":[174,202],"construction":[177,186,218],"process":[178],"itself":[179,220],"be":[181],"learned:":[182],"fine-tuning":[183],"Qwen3.5-35B-A3B":[184],"traces":[187],"increases":[188],"executable-world":[189],"authoring":[190],"success":[191],"3.3%":[193],"83.3%":[195],"held-out":[197],"These":[200],"results":[201],"scenario-grounded":[204],"provide":[207],"useful":[208],"generalizable":[210],"learning":[211],"signals":[212],"beyond":[213],"benchmark-specific":[214],"training,":[215],"while":[216],"their":[217],"become":[221],"learnable":[223],"capability.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-25T00:00:00"}