{"id":"https://openalex.org/W7223129641","doi":"https://doi.org/10.48550/arxiv.2610.27435","title":"Harness Self-Evolution for Long-Horizon Terminal Agents","display_name":"Harness Self-Evolution for Long-Horizon Terminal Agents","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223129641","doi":"https://doi.org/10.48550/arxiv.2610.27435"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.27435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27435","pdf_url":"https://arxiv.org/pdf/2610.27435","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/2610.27435","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159172072","display_name":"Ruhan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Ruhan","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159191670","display_name":"Yucheng Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159220587","display_name":"Zongxia Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zongxia","raw_affiliation_strings":["University of Georgia","University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Georgia","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159216209","display_name":"Junyao Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang, Junyao","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159212078","display_name":"Zhongzhi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zhongzhi","raw_affiliation_strings":["University of Georgia","University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Georgia","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159214244","display_name":"Yue Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu, Yue","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071533156","display_name":"Haitao Mi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mi, Haitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141013450","display_name":"Dongruo Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Dongruo","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135928747","display_name":"Leoweiliang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leoweiliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.4246000051498413,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.4246000051498413,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.13570000231266022,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0828000009059906,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/agent-harnesses","display_name":"agent harnesses","score":0.8989999890327454},{"id":"https://openalex.org/keywords/failure-analysis","display_name":"failure analysis","score":0.5320000052452087},{"id":"https://openalex.org/keywords/task-reliability","display_name":"task reliability","score":0.4359999895095825},{"id":"https://openalex.org/keywords/agent-trajectories","display_name":"agent trajectories","score":0.49900001287460327},{"id":"https://openalex.org/keywords/runtime-monitoring","display_name":"runtime monitoring","score":0.703000009059906},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430999875068665},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7027999758720398},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4462999999523163},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3626999855041504},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.27435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27435","pdf_url":"https://arxiv.org/pdf/2610.27435","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.2610.27435","doi":"https://doi.org/10.48550/arxiv.2610.27435","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.27435","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.27435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27435","pdf_url":"https://arxiv.org/pdf/2610.27435","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/W7223129641.pdf","grobid_xml":"https://content.openalex.org/works/W7223129641.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W4304195432","https://openalex.org/W4387145092","https://openalex.org/W4387430850","https://openalex.org/W4399836817","https://openalex.org/W4402500863","https://openalex.org/W4403344644","https://openalex.org/W4403571374","https://openalex.org/W4412505633","https://openalex.org/W4416020713","https://openalex.org/W4416411532","https://openalex.org/W4417129489","https://openalex.org/W4417150440","https://openalex.org/W7084066371","https://openalex.org/W7103754783","https://openalex.org/W7125193990","https://openalex.org/W7127528697","https://openalex.org/W7128697492","https://openalex.org/W7130615426","https://openalex.org/W7147383744","https://openalex.org/W7158100772","https://openalex.org/W7160949450","https://openalex.org/W7163637799","https://openalex.org/W7164008618","https://openalex.org/W7166844691","https://openalex.org/W7168172066","https://openalex.org/W7168361355","https://openalex.org/W7168571411","https://openalex.org/W7170039223","https://openalex.org/W7172337529","https://openalex.org/W7201839693","https://openalex.org/W7206192636","https://openalex.org/W7206206100","https://openalex.org/W7212293382","https://openalex.org/W7213359549","https://openalex.org/W7214002283","https://openalex.org/W7214086309","https://openalex.org/W7220408558","https://openalex.org/W7221774961","https://openalex.org/W7222532804"],"related_works":["https://openalex.org/W7163637799","https://openalex.org/W7204215770","https://openalex.org/W7171771814","https://openalex.org/W7171689098","https://openalex.org/W7172415314","https://openalex.org/W7172444541","https://openalex.org/W7212406378","https://openalex.org/W7152129790","https://openalex.org/W7221814687","https://openalex.org/W7164848732"],"abstract_inverted_index":{"Long-horizon":[0],"terminal":[1],"agents":[2],"may":[3],"solve":[4],"a":[5,24,34,77,164,203],"task":[6,145,178],"in":[7,111],"one":[8],"run":[9],"yet":[10],"fail":[11],"across":[12,114,182,225],"repeated":[13,144],"runs.":[14],"Stochastic":[15],"errors":[16],"can":[17,219],"propagate":[18],"through":[19],"actions":[20,84],"and":[21,28,53,92,104,125,135,143,167,180,188,191],"context,":[22],"creating":[23],"gap":[25],"between":[26],"capability":[27],"reliable":[29,224],"execution.":[30],"We":[31,176],"present":[32],"RiseHarness,":[33],"framework":[35],"for":[36,65,122],"iteratively":[37],"improving":[38],"agent":[39,70],"harnesses":[40],"with":[41,50,72,86,148,197],"model":[42,83,134,205],"weights":[43],"fixed.":[44],"It":[45],"focuses":[46],"on":[47],"flipping":[48],"tasks":[49],"both":[51],"successful":[52,61],"failed":[54],"runs":[55,62],"under":[56],"the":[57,132,152,198,207],"same":[58,199],"configuration,":[59],"using":[60],"as":[63,128,206],"references":[64,130],"failure":[66],"analysis.":[67],"RiseHarness":[68,116,201],"combines":[69],"trajectories":[71],"internal":[73],"harness":[74,102,120,166,185,210],"traces":[75],"from":[76,160],"runtime":[78],"monitor":[79],"to":[80,101,131,172,194,215],"examine":[81],"how":[82,213],"interact":[85],"command":[87],"execution,":[88],"feedback,":[89],"context":[90],"management,":[91],"completion":[93],"decisions.":[94],"A":[95],"Harness":[96],"Handbook":[97],"links":[98],"this":[99],"evidence":[100,171,187],"behaviors":[103],"source":[105],"code,":[106],"helping":[107],"identify":[108],"recurring":[109],"problems":[110],"mechanisms":[112,159,218],"shared":[113,216],"tasks.":[115,226],"then":[117],"searches":[118],"other":[119],"frameworks":[121,162],"relevant":[123],"implementations":[124],"adapts":[126],"them":[127],"design":[129],"current":[133],"execution":[136,170,186],"protocol.":[137],"Candidate":[138],"changes":[139,214],"undergo":[140],"behavioral":[141],"checks":[142],"evaluation;":[146],"versions":[147],"measured":[149],"gains":[150],"seed":[151],"next":[153],"iteration.":[154],"This":[155],"loop":[156],"integrates":[157],"suitable":[158],"different":[161],"into":[163],"single":[165],"uses":[168],"new":[169],"guide":[173],"further":[174],"changes.":[175],"evaluate":[177],"success":[179],"reliability":[181],"models,":[183],"ablate":[184],"external":[189],"research,":[190],"test":[192],"transfer":[193],"unseen":[195],"benchmarks":[196],"model.":[200],"treats":[202],"specific":[204],"unit":[208],"of":[209],"adaptation,":[211],"studying":[212],"interaction":[217],"make":[220],"existing":[221],"capabilities":[222],"more":[223]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-22T00:00:00"}