{"id":"https://openalex.org/W7164018301","doi":"https://doi.org/10.48550/arxiv.2606.07995","title":"Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR","display_name":"Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVR","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7164018301","doi":"https://doi.org/10.48550/arxiv.2606.07995"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.07995","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07995","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.07995","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100662332","display_name":"Hongye Liu","orcid":"https://orcid.org/0000-0003-2558-7939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hongye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050956010","display_name":"Rongmei Lin","orcid":"https://orcid.org/0000-0002-3325-5590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Rongmei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138275370","display_name":"Anurag Kashyap","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kashyap, Anurag","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033157677","display_name":"Hejie Cui","orcid":"https://orcid.org/0000-0001-6388-2619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Hejie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138278023","display_name":"Ricardo Henao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henao, Ricardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001039604","display_name":"Besnik Fetahu","orcid":"https://orcid.org/0000-0002-3343-7992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fetahu, Besnik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138214877","display_name":"Bing Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.2615000009536743,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.2615000009536743,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.10859999805688858,"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/T10028","display_name":"Topic Modeling","score":0.08780000358819962,"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/benchmarking","display_name":"Benchmarking","score":0.6205000281333923},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.475600004196167},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.39649999141693115},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.3962000012397766},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3901999890804291},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.37880000472068787},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.37880000472068787},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.36980000138282776},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.3513999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215000033378601},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6205000281333923},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4449999928474426},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3962000012397766},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.07995","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07995","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.07995","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07995","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,"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"},"sustainable_development_goals":[{"score":0.4178013801574707,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"customer":[1,55],"shopping":[2,9,12,90,128],"trajectories":[3,32,59,159],"is":[4],"essential":[5],"for":[6,37,141,198],"enabling":[7,103],"personalized":[8],"experiences.":[10],"However,":[11],"records":[13],"(i.e.,":[14],"customer's":[15],"search,":[16],"clicks,":[17],"purchases,":[18],"etc.)":[19],"often":[20],"span":[21],"long":[22,31,127],"time":[23],"horizons":[24],"over":[25,126],"multiple":[26],"years,":[27],"resulting":[28],"in":[29,124],"extremely":[30],"that":[33,192],"pose":[34],"significant":[35],"challenges":[36],"existing":[38,49],"large":[39,61],"language":[40],"models":[41],"(LLMs).":[42],"Despite":[43],"the":[44,166,182],"importance":[45],"of":[46,96,106,116,187],"this":[47,74],"problem,":[48],"benchmarks":[50],"are":[51,64],"limited":[52],"to":[53,68,98,168,203],"short":[54],"trajectories,":[56],"while":[57],"real-world":[58,85],"from":[60,84],"e-commerce":[62],"platforms":[63],"rarely":[65],"accessible":[66],"due":[67],"data":[69],"privacy":[70],"constraints.":[71],"To":[72,131],"address":[73,132],"gap,":[75],"we":[76,119,135],"introduce":[77],"ShopTrajQA,":[78],"a":[79,137,146],"long-context":[80],"evaluation":[81,105],"benchmark":[82],"constructed":[83],"product":[86],"information":[87],"and":[88,100,164,171,200],"simulated":[89],"trajectories.":[91],"The":[92],"dataset":[93],"includes":[94],"variants":[95],"up":[97],"32k":[99],"64k":[101],"tokens,":[102],"systematic":[104],"model":[107],"robustness":[108],"under":[109],"varying":[110],"context":[111,143],"lengths.":[112],"Through":[113],"comprehensive":[114],"benchmarking":[115],"frontier":[117],"LLMs,":[118],"identify":[120],"critical":[121],"performance":[122,197],"gaps":[123],"reasoning":[125,206],"trajectory":[129],"data.":[130],"these":[133],"challenges,":[134],"propose":[136],"Customer":[138],"Agent":[139],"Framework":[140],"ultra-long":[142],"management.":[144],"Leveraging":[145],"Reinforcement":[147],"Learning":[148],"with":[149],"Verifiable":[150],"Rewards":[151],"(RLVR)":[152],"agentic":[153],"training":[154],"paradigm,":[155],"our":[156,193],"approach":[157],"stores":[158],"as":[160],"external":[161],"local":[162],"files":[163],"trains":[165],"agent":[167],"autonomously":[169],"retrieve":[170],"parse":[172],"them":[173],"through":[174],"code-interpreter":[175],"interactions":[176],"(e.g.,":[177],"SQL":[178],"queries),":[179],"effectively":[180],"bypassing":[181],"fixed":[183],"in-context":[184],"window":[185],"constraints":[186],"LLMs.":[188],"Experimental":[189],"results":[190],"demonstrate":[191],"framework":[194],"achieves":[195],"strong":[196],"ShopTrajQA":[199],"shows":[201],"generalization":[202],"other":[204],"complex":[205],"tasks.":[207]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}