{"id":"https://openalex.org/W7223999747","doi":"https://doi.org/10.48550/arxiv.2610.34938","title":"How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation","display_name":"How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223999747","doi":"https://doi.org/10.48550/arxiv.2610.34938"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.34938","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.34938","pdf_url":"https://arxiv.org/pdf/2610.34938","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/2610.34938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134124070","display_name":"Christoph Treude","orcid":"https://orcid.org/0000-0002-6919-2149","observed_orcids":["https://orcid.org/0000-0002-6919-2149"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Treude, Christoph","raw_affiliation_strings":["Singapore Management University Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033132966","display_name":"Sebastian Baltes","orcid":"https://orcid.org/0000-0002-2442-7522","observed_orcids":["https://orcid.org/0000-0002-2442-7522"]},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Baltes, Sebastian","raw_affiliation_strings":["Heidelberg University Heidelberg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heidelberg University Heidelberg , Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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/T10260","display_name":"Software Engineering Research","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.003100000089034438,"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/ai-coding-agents","display_name":"coding agents","score":0.9869999885559082},{"id":"https://openalex.org/keywords/self-evolution","display_name":"self-evolution","score":0.8029999732971191},{"id":"https://openalex.org/keywords/claude-code","display_name":"Claude Code","score":0.7770000100135803},{"id":"https://openalex.org/keywords/swe-bench","display_name":"SWE-bench","score":0.7129999995231628},{"id":"https://openalex.org/keywords/bug-fixing","display_name":"bug fixes","score":0.375},{"id":"https://openalex.org/keywords/code-review","display_name":"code review","score":0.4129999876022339},{"id":"https://openalex.org/keywords/linting","display_name":"linting","score":0.4059999883174896},{"id":"https://openalex.org/keywords/configuration-changes","display_name":"configuration changes","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.6151000261306763},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5985000133514404},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5357999801635742},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34549999237060547},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.28610000014305115},{"id":"https://openalex.org/C159198006","wikidata":"https://www.wikidata.org/wiki/Q1532172","display_name":"Technical debt","level":4,"score":0.28600001335144043},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C133112747","wikidata":"https://www.wikidata.org/wiki/Q7251931","display_name":"Protocol analysis","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.34938","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.34938","pdf_url":"https://arxiv.org/pdf/2610.34938","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.2610.34938","doi":"https://doi.org/10.48550/arxiv.2610.34938","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.34938","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:2610.34938","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.34938","pdf_url":"https://arxiv.org/pdf/2610.34938","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/W7223999747.pdf","grobid_xml":"https://content.openalex.org/works/W7223999747.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7172533549","https://openalex.org/W7131850018","https://openalex.org/W7221820792","https://openalex.org/W7162458615","https://openalex.org/W7158100772","https://openalex.org/W7223859883","https://openalex.org/W7202296357","https://openalex.org/W7163683658","https://openalex.org/W7140230117","https://openalex.org/W7168699653"],"abstract_inverted_index":{"Coding":[0],"agents":[1],"can":[2],"adapt":[3],"their":[4,26],"harnesses,":[5],"the":[6,78,94,112,129,136,139,145],"software,":[7],"configuration,":[8],"and":[9,47,51,57,85,101,156,170,185],"instructions":[10],"used":[11],"to":[12,42,108,176,186],"run":[13],"them,":[14],"based":[15],"on":[16,28,64,71,90,161,182],"experience":[17],"from":[18,81,93],"earlier":[19],"tasks,":[20],"but":[21,114],"whether":[22,58,178],"these":[23],"adaptations":[24],"improve":[25],"behavior":[27],"later":[29,65,91,183],"tasks":[30,184],"remains":[31],"unclear.":[32],"We":[33,67],"study":[34],"\\retro,":[35,82],"a":[36,44,121,179],"skill":[37],"that":[38,191],"asks":[39],"an":[40,109],"agent":[41],"review":[43],"completed":[45],"session":[46],"propose":[48],"harness":[49,88],"changes,":[50],"ask":[52],"what":[53,125],"changes":[54,60,89,143,158,190],"it":[55,173],"proposes":[56],"implemented":[59,83],"reduce":[61],"repeated":[62],"work":[63,160],"tasks.":[66],"ran":[68],"Claude":[69],"Code":[70],"30":[72],"SWE-bench":[73],"Verified":[74],"issues,":[75],"qualitatively":[76],"coded":[77],"125":[79],"proposals":[80,106,119],"24,":[84],"evaluated":[86],"12":[87],"issues":[92],"same":[95],"repositories":[96],"in":[97,111,132],"fresh":[98],"sessions":[99,134],"with":[100],"without":[102,135],"each":[103],"change.":[104],"Most":[105],"referred":[107],"event":[110],"session,":[113],"18":[115],"of":[116,124],"43":[117],"lint-related":[118],"recommended":[120],"practice":[122],"regardless":[123],"had":[126],"happened.":[127],"Among":[128],"seven":[130],"evaluations":[131],"which":[133],"change":[137,180],"encountered":[138],"targeted":[140,146],"problem,":[141],"two":[142],"eliminated":[144],"action,":[147],"one":[148],"reduced":[149],"its":[150],"occurrence,":[151],"four":[152],"showed":[153],"no":[154],"reduction,":[155],"some":[157],"added":[159],"unrelated":[162],"issues.":[163],"Harness":[164],"self-evolution":[165],"requires":[166],"more":[167],"than":[168],"generating":[169],"implementing":[171],"changes:":[172],"needs":[174],"ways":[175],"establish":[177],"helps":[181],"revise":[187],"or":[188],"remove":[189],"do":[192],"not.":[193]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-28T00:00:00"}
