{"id":"https://openalex.org/W7214765789","doi":"https://doi.org/10.48550/arxiv.2609.34557","title":"SkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents","display_name":"SkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214765789","doi":"https://doi.org/10.48550/arxiv.2609.34557"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34557","pdf_url":"https://arxiv.org/pdf/2609.34557","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135876135","display_name":"Bingqing Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jiang, Bingqing","raw_affiliation_strings":["The University of Hong Kong","WeChat , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"WeChat , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153506496","display_name":"Guoxi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Guoxi","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153539399","display_name":"Jasper Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jasper","raw_affiliation_strings":["WeChat , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153528256","display_name":"Auric Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Auric","raw_affiliation_strings":["WeChat , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067986384","display_name":"Bingning Wang","orcid":"https://orcid.org/0009-0007-7748-7098","observed_orcids":["https://orcid.org/0009-0007-7748-7098","https://orcid.org/0000-0003-4095-5082"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Bingning","raw_affiliation_strings":["WeChat , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153433493","display_name":"Tianyi Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lin, Tianyi","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112840113","display_name":"Zichao Yu","orcid":"https://orcid.org/0009-0005-8880-279X","observed_orcids":["https://orcid.org/0009-0005-8880-279X"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu, Zichao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153421920","display_name":"Yujin Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Han, Yujin","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073042787","display_name":"Ziye Ma","orcid":"https://orcid.org/0000-0002-3605-3505","observed_orcids":["https://orcid.org/0000-0002-3605-3505"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ma, Ziye","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085848346","display_name":"Difan Zou","orcid":"https://orcid.org/0000-0002-6544-2593","observed_orcids":["https://orcid.org/0000-0002-6544-2593"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zou, Difan","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.34470000863075256,"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":0.34470000863075256,"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":0.305400013923645,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08889999985694885,"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/multimodal-agents","display_name":"multimodal agents","score":0.8320000171661377},{"id":"https://openalex.org/keywords/procedural-guidance","display_name":"procedural guidance","score":0.6690000295639038},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.6809999942779541},{"id":"https://openalex.org/keywords/long-horizon-planning","display_name":"long-horizon planning","score":0.9919999837875366}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.9496999979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649999856948853},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6363000273704529},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2745000123977661}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34557","pdf_url":"https://arxiv.org/pdf/2609.34557","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.2609.34557","doi":"https://doi.org/10.48550/arxiv.2609.34557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34557","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:2609.34557","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34557","pdf_url":"https://arxiv.org/pdf/2609.34557","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":[{"score":0.4156000018119812,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214765789.pdf","grobid_xml":"https://content.openalex.org/works/W7214765789.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4391631327","https://openalex.org/W4414975272","https://openalex.org/W4414990013","https://openalex.org/W4415271129","https://openalex.org/W4416021371","https://openalex.org/W4416780398","https://openalex.org/W4417350470","https://openalex.org/W7079299863","https://openalex.org/W7126224745","https://openalex.org/W7127415714","https://openalex.org/W7128545450","https://openalex.org/W7131862632","https://openalex.org/W7133517971","https://openalex.org/W7139036837","https://openalex.org/W7148945997","https://openalex.org/W7150843745","https://openalex.org/W7154202256","https://openalex.org/W7154299763","https://openalex.org/W7160937593","https://openalex.org/W7161018565","https://openalex.org/W7161144181","https://openalex.org/W7161258139","https://openalex.org/W7161712591","https://openalex.org/W7162283228","https://openalex.org/W7163174640","https://openalex.org/W7165385035","https://openalex.org/W7165678886","https://openalex.org/W7165692494","https://openalex.org/W7168511125","https://openalex.org/W7169575253","https://openalex.org/W7201837771"],"related_works":["https://openalex.org/W7167209728","https://openalex.org/W7168963557","https://openalex.org/W7213286606","https://openalex.org/W7160957554","https://openalex.org/W7203491292","https://openalex.org/W7135214336","https://openalex.org/W7212234129","https://openalex.org/W7165678886","https://openalex.org/W7204899727","https://openalex.org/W7164828440"],"abstract_inverted_index":{"Recent":[0],"work":[1],"incorporates":[2],"reusable":[3],"skills":[4,169],"distilled":[5],"from":[6,62],"past":[7],"interactions":[8],"into":[9],"multimodal":[10,107,154],"agent":[11,155],"training,":[12],"providing":[13,35],"procedural":[14],"guidance":[15,101,135,173],"for":[16,38,174],"long-horizon":[17],"planning":[18,175],"and":[19,59,81,102,114,119,144,176],"tool":[20,115,177],"use.":[21],"However,":[22],"policy":[23,143],"optimization":[24],"in":[25],"these":[26],"methods":[27],"remains":[28],"driven":[29],"primarily":[30],"by":[31,66],"sparse":[32],"outcome":[33],"rewards,":[34],"little":[36],"supervision":[37],"intermediate":[39,48],"decisions.":[40],"Rubric-based":[41],"rewards":[42,121],"address":[43],"this":[44,89],"limitation":[45],"through":[46,98,137],"explicit":[47],"criteria,":[49],"but":[50],"reliable":[51],"rubrics":[52],"are":[53],"difficult":[54],"to":[55,79,122],"construct":[56],"at":[57],"scale":[58],"often":[60],"disconnected":[61],"the":[63,67,123],"procedure":[64],"followed":[65],"actor.":[68],"We":[69,126],"observe":[70],"that":[71,133,167],"a":[72,141],"well-structured":[73],"skill":[74,97],"naturally":[75],"specifies":[76],"both":[77],"how":[78],"act":[80],"what":[82],"successful":[83],"execution":[84],"should":[85],"achieve.":[86],"Based":[87],"on":[88],"insight,":[90],"we":[91],"introduce":[92,128],"SkillRubric,":[93],"which":[94],"represents":[95],"each":[96],"aligned":[99],"actor-facing":[100],"an":[103,129],"evaluator-facing":[104],"rubric.":[105],"A":[106],"verifier":[108],"evaluates":[109],"skill-defined":[110],"goals":[111],"using":[112],"screenshots":[113],"outputs,":[116],"assigning":[117],"completion":[118],"progress":[120],"responsible":[124],"turns.":[125],"further":[127,165],"alternating":[130],"co-evolution":[131],"scheme":[132],"validates":[134],"revisions":[136,146],"paired":[138,163],"rollouts":[139,164],"under":[140,148],"frozen":[142],"rubric":[145],"offline":[147],"fixed":[149],"guidance.":[150],"Experiments":[151],"across":[152],"diverse":[153],"benchmarks":[156],"demonstrate":[157],"consistent":[158],"performance":[159],"gains,":[160],"while":[161],"controlled":[162],"show":[166],"evolved":[168],"provide":[170],"more":[171],"effective":[172],"use":[178],"than":[179],"their":[180],"preceding":[181],"versions.":[182]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}