{"id":"https://openalex.org/W7204128505","doi":"https://doi.org/10.48550/arxiv.2608.20797","title":"Automated Trajectory Evaluation for Mobile Agents via Step-Level Consequence Reasoning and Aggregation","display_name":"Automated Trajectory Evaluation for Mobile Agents via Step-Level Consequence Reasoning and Aggregation","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204128505","doi":"https://doi.org/10.48550/arxiv.2608.20797"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20797","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20797","pdf_url":"https://arxiv.org/pdf/2608.20797","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141195452","display_name":"Pengshuai Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094623","display_name":"Jiuquan Iron & Steel (China)","ror":"https://ror.org/00mgrqp66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Pengshuai","raw_affiliation_strings":["Equal Contribution ,","Jiutian Research , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal Contribution ,","institution_ids":[]},{"raw_affiliation_string":"Jiutian Research , China","institution_ids":["https://openalex.org/I4210094623"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148038300","display_name":"Zijing Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094623","display_name":"Jiuquan Iron & Steel (China)","ror":"https://ror.org/00mgrqp66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Zijing","raw_affiliation_strings":["Equal Contribution ,","Jiutian Research , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal Contribution ,","institution_ids":[]},{"raw_affiliation_string":"Jiutian Research , China","institution_ids":["https://openalex.org/I4210094623"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141194799","display_name":"Xue Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094623","display_name":"Jiuquan Iron & Steel (China)","ror":"https://ror.org/00mgrqp66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Xue","raw_affiliation_strings":["Jiutian Research , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiutian Research , China","institution_ids":["https://openalex.org/I4210094623"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041871065","display_name":"Benhui Zhuang","orcid":"https://orcid.org/0000-0002-5062-2460","observed_orcids":["https://orcid.org/0000-0002-5062-2460"]},"institutions":[{"id":"https://openalex.org/I4210094623","display_name":"Jiuquan Iron & Steel (China)","ror":"https://ror.org/00mgrqp66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang, Benhui","raw_affiliation_strings":["Jiutian Research , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiutian Research , China","institution_ids":["https://openalex.org/I4210094623"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147926594","display_name":"Bo Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094623","display_name":"Jiuquan Iron & Steel (China)","ror":"https://ror.org/00mgrqp66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Bo","raw_affiliation_strings":["Jiutian Research , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiutian Research , China","institution_ids":["https://openalex.org/I4210094623"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136473316","display_name":"Junlan Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094623","display_name":"Jiuquan Iron & Steel (China)","ror":"https://ror.org/00mgrqp66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210094623"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Junlan","raw_affiliation_strings":["Jiutian Research , China","Mobile ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiutian Research , China","institution_ids":["https://openalex.org/I4210094623"]},{"raw_affiliation_string":"Mobile ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210094623"],"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.1404999941587448,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.1404999941587448,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10790000110864639,"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/T12203","display_name":"Mobile Agent-Based Network Management","score":0.0885000005364418,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/operational-safety-assessment","display_name":"operational safety assessment","score":0.8870000243186951},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813000082969666},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6568999886512756},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C2781188742","wikidata":"https://www.wikidata.org/wiki/Q605384","display_name":"Crate","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4413999915122986},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33719998598098755},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2705000042915344}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20797","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20797","pdf_url":"https://arxiv.org/pdf/2608.20797","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.20797","doi":"https://doi.org/10.48550/arxiv.2608.20797","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20797","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:2608.20797","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20797","pdf_url":"https://arxiv.org/pdf/2608.20797","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204128505.pdf","grobid_xml":"https://content.openalex.org/works/W7204128505.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7102395291","https://openalex.org/W4415334925","https://openalex.org/W7172099397","https://openalex.org/W4403333972","https://openalex.org/W4415540031","https://openalex.org/W7138934980","https://openalex.org/W7214068069","https://openalex.org/W7151843496","https://openalex.org/W7161387097","https://openalex.org/W4417300244"],"abstract_inverted_index":{"Evaluating":[0],"language-guided":[1],"mobile":[2,58],"agents":[3],"has":[4],"recently":[5],"shifted":[6],"from":[7],"rule-based":[8],"to":[9,12,29,101,118],"model-based":[10],"approaches":[11],"achieve":[13],"scalable":[14],"and":[15,67,82,129,134],"automated":[16,57],"assessments.":[17],"However,":[18],"existing":[19],"holistic":[20],"evaluation":[21,60,105,112],"paradigms":[22],"process":[23],"entire":[24],"trajectories":[25],"at":[26,87,170],"once,":[27],"leading":[28],"substantial":[30],"context":[31],"overload.":[32],"Moreover,":[33],"they":[34],"primarily":[35],"focus":[36],"on":[37,145,158],"task":[38,107],"completion":[39],"while":[40,151],"overlooking":[41],"operational":[42,121],"safety.":[43],"To":[44],"address":[45],"these":[46],"limitations,":[47],"we":[48,114],"introduce":[49],"CRATE,":[50],"a":[51,71],"novel":[52],"two-stage":[53],"VLM-as-judge":[54],"framework":[55],"for":[56,120],"agent":[59],"that":[61],"is":[62,95,168],"compatible":[63],"with":[64,163],"both":[65,132],"open-":[66],"closed-source":[68],"models.":[69],"Leveraging":[70],"step-level":[72,92],"consequence":[73],"reasoning":[74],"mechanism,":[75],"CRATE":[76,117,133,139],"independently":[77],"extracts":[78],"task-relevant":[79],"visual":[80],"clues":[81],"infers":[83],"action-conditioned":[84],"state":[85],"changes":[86],"each":[88],"step.":[89],"The":[90],"resulting":[91],"textual":[93],"evidence":[94],"then":[96],"synthesized":[97],"through":[98],"trajectory-level":[99],"aggregation":[100],"deliver":[102],"an":[103,141,154],"evidence-grounded":[104],"of":[106,131,143,156],"completion.":[108],"Building":[109],"upon":[110],"this":[111],"scheme,":[113],"further":[115],"extend":[116],"CRATE-S":[119,152],"safety":[122],"assessment.":[123],"Extensive":[124],"experiments":[125],"validate":[126],"the":[127],"effectiveness":[128],"robustness":[130],"CRATE-S.":[135],"Powered":[136],"by":[137,149],"Qwen2.5-VL-72B-Instruct,":[138],"achieves":[140],"F1-score":[142,155],"0.833":[144],"AndroidWorld":[146],"(outperforming":[147],"SPA-Bench":[148],"20%),":[150],"reaches":[153],"0.697":[157],"MobileRisk,":[159],"demonstrating":[160],"strong":[161],"alignment":[162],"benchmark":[164],"ground":[165],"truths.":[166],"Code":[167],"available":[169],"https://anonymous.4open.science/r/CRATE-D580.":[171]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-25T00:00:00"}