{"id":"https://openalex.org/W7163152152","doi":"https://doi.org/10.48550/arxiv.2606.01859","title":"Improving LLM-Based Go Code Review through Issue-List Generation and Context Augmentation","display_name":"Improving LLM-Based Go Code Review through Issue-List Generation and Context Augmentation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163152152","doi":"https://doi.org/10.48550/arxiv.2606.01859"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.01859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.01859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047722053","display_name":"Kexin Sun","orcid":"https://orcid.org/0009-0004-1344-5444"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Kexin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023929959","display_name":"Yucong Guan","orcid":"https://orcid.org/0000-0002-7412-6082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Yucong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137620579","display_name":"Jiaqi Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137683042","display_name":"Hongyu Kuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuang, Hongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073751973","display_name":"Guoping Rong","orcid":"https://orcid.org/0000-0003-4576-0524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong, Guoping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101193832","display_name":"Dong Shao","orcid":"https://orcid.org/0000-0001-6500-0341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137661218","display_name":"He Zhang","orcid":"https://orcid.org/0009-0000-5318-5676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137665523","display_name":"Xiaoxing Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xiaoxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137692839","display_name":"Christoph Treude","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Treude, Christoph","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/T10260","display_name":"Software Engineering Research","score":0.4537999927997589,"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":0.4537999927997589,"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/T10028","display_name":"Topic Modeling","score":0.35089999437332153,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.019099999219179153,"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/pruning","display_name":"Pruning","score":0.7749999761581421},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7164000272750854},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6672999858856201},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3871000111103058},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.31130000948905945}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7749999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7164000272750854},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6672999858856201},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.01859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.01859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.01859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0,49],"have":[1],"shown":[2],"strong":[3],"potential":[4,52],"for":[5,168],"automating":[6],"code":[7,32,73,130,150],"review,":[8,198],"yet":[9],"their":[10],"practical":[11,117,181],"utility":[12],"depends":[13],"heavily":[14],"on":[15,123],"the":[16,58,112,133,139,148,153,185,234,243,256,260],"design":[17],"of":[18,72,216,237],"generation":[19,35,101],"and":[20,37,80,86,99,106,200,204,232],"context":[21,74,84,226],"strategies.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,94,159],"investigate":[27],"how":[28,88,137],"to":[29,102,110,249,264],"improve":[30,103],"LLM-based":[31],"review":[33,45,104,126,169,177,222],"through":[34],"strategy":[36],"contextual":[38],"augmentation.":[39],"We":[40,66,119],"first":[41],"propose":[42],"an":[43],"issue-list":[44,197],"paradigm,":[46],"in":[47],"which":[48],"enumerate":[50],"all":[51],"issues":[53],"rather":[54],"than":[55],"reporting":[56],"only":[57],"single":[59],"most":[60],"important":[61],"one":[62,145],"(i.e.,":[63],"primary-issue":[64,221],"review).":[65],"then":[67],"systematically":[68],"compare":[69],"three":[70],"types":[71],"augmentation":[75],"--":[76,85],"neighboring,":[77],"LSP-based":[78],"semantics,":[79],"IR-based":[81],"similar":[82,201],"co-change":[83,202],"study":[87],"they":[89],"influence":[90],"issue":[91],"discovery.":[92],"Finally,":[93],"integrate":[95],"candidates":[96],"from":[97,247],"no-context":[98],"context-enhanced":[100],"coverage,":[105],"introduce":[107],"refinement-guided":[108,240],"pruning":[109,241],"keep":[111],"candidate":[113,140,205,245,261],"list":[114,141,262],"at":[115,143,251],"a":[116,164,180,212],"size.":[118],"evaluate":[120,160],"our":[121,193],"approach":[122],"1,438":[124],"Go":[125],"instances":[127],"using":[128],"downstream":[129],"refinement":[131,209],"as":[132,152,172,174],"main":[134],"metric,":[135],"i.e.,":[136],"often":[138],"contains":[142],"least":[144],"comment":[146,170],"inducing":[147],"same":[149,186],"change":[151],"final":[154],"human":[155,176],"revision.":[156],"For":[157],"comparison,":[158],"comments":[161,178],"by":[162],"CodeReviewer,":[163],"model":[165],"trained":[166],"specifically":[167],"generation,":[171],"well":[173],"ground-truth":[175],"(as":[179],"upper":[182],"bound),":[183],"under":[184],"refinement-based":[187],"evaluation.":[188],"The":[189],"results":[190],"show":[191],"that":[192],"best":[194],"configuration,":[195],"combining":[196],"neighboring":[199],"context,":[203],"integration,":[206],"reaches":[207],"28.00%":[208],"exact":[210],"match,":[211],"statistically":[213],"significant":[214],"gain":[215],"+10.85":[217],"percentage":[218],"points":[219],"over":[220],"without":[223],"any":[224],"additional":[225],"(17.15%),":[227],"substantially":[228],"outperforming":[229],"CodeReviewer":[230],"(15.02%)":[231],"approaching":[233],"human-oracle":[235],"ceiling":[236],"36.09%.":[238],"Our":[239],"reduces":[242],"average":[244],"count":[246],"7.2":[248],"3.1":[250],"top-5":[252],"while":[253],"retaining":[254],"nearly":[255],"full":[257],"benefit,":[258],"making":[259],"easier":[263],"inspect.":[265]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}