{"id":"https://openalex.org/W7161997019","doi":"https://doi.org/10.1145/3786167.3788410","title":"PerfBench: Can Agents Resolve Real-World Performance Bugs?","display_name":"PerfBench: Can Agents Resolve Real-World Performance Bugs?","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7161997019","doi":"https://doi.org/10.1145/3786167.3788410"},"language":null,"primary_location":{"id":"doi:10.1145/3786167.3788410","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786167.3788410","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Workshop on Agentic Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786167.3788410","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044601242","display_name":"Spandan Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spandan Garg","raw_affiliation_strings":["Microsoft Corporation, Redmond, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0009-0140-2785","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056155621","display_name":"Roshanak Zilouchian Moghaddam","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roshanak Zilouchian Moghaddam","raw_affiliation_strings":["Microsoft Corporation, Redmond, Washington, USA"],"raw_orcid":"https://orcid.org/0009-0000-2268-5897","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085284883","display_name":"Neel Sundaresan","orcid":"https://orcid.org/0000-0002-0394-7588"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neel Sundaresan","raw_affiliation_strings":["Microsoft Corporation, Redmond, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0002-0394-7588","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81482046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6797999739646912,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6797999739646912,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.23229999840259552,"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/T10260","display_name":"Software Engineering Research","score":0.020899999886751175,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8029000163078308},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7505999803543091},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5440000295639038},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46880000829696655},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43790000677108765},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.32829999923706055}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8029000163078308},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7505999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992999911308289},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3772999942302704},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C178059732","wikidata":"https://www.wikidata.org/wiki/Q1982529","display_name":"Software performance testing","level":5,"score":0.2766999900341034},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C141571065","wikidata":"https://www.wikidata.org/wiki/Q1771949","display_name":"Performance measurement","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786167.3788410","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786167.3788410","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Workshop on Agentic Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786167.3788410","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786167.3788410","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Workshop on Agentic Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1976006326","https://openalex.org/W2122947685","https://openalex.org/W2125341657","https://openalex.org/W2130655713","https://openalex.org/W2153684747","https://openalex.org/W2163661306","https://openalex.org/W2795030435","https://openalex.org/W3134445958","https://openalex.org/W3165074812","https://openalex.org/W3185341429","https://openalex.org/W3194184668","https://openalex.org/W4234815652","https://openalex.org/W4238111449","https://openalex.org/W4255632703","https://openalex.org/W4308642031"],"related_works":[],"abstract_inverted_index":{"Performance":[0],"bugs":[1],"are":[2,127],"inefficiencies":[3],"in":[4,25,32,114,227],"software":[5],"that":[6,77,89,139,184],"waste":[7],"computational":[8],"resources":[9],"without":[10],"causing":[11],"functional":[12,41],"failures,":[13],"making":[14],"them":[15],"particularly":[16],"challenging":[17,218],"to":[18,45,49,92,123,192],"detect":[19],"and":[20,43,51,98,109,170,172,196],"fix.":[21,111],"While":[22],"recent":[23],"advances":[24],"Software":[26],"Engineering":[27],"agents":[28,91,143,226],"have":[29],"shown":[30],"promise":[31],"automated":[33],"bug":[34],"fixing,":[35],"existing":[36,75],"benchmarks":[37,76,97],"primarily":[38],"focus":[39],"on":[40,72,79,160,179],"correctness":[42],"fail":[44],"evaluate":[46],"agents\u2019":[47],"abilities":[48],"identify":[50],"resolve":[52],"non-functional":[53],"issues":[54],"like":[55],"performance":[56,66,96,146,207],"bugs.":[57],"We":[58,163,182],"introduce":[59],"PerfBench,":[60],"a":[61,85,155,174,217],"benchmark":[62,193,199],"comprising":[63],"81":[64],"real-world":[65,134],"bug-fixing":[67],"tasks":[68],"from":[69,118],"popular.NET":[70],"repositories":[71],"GitHub.":[73],"Unlike":[74],"rely":[78],"pre-existing":[80],"test":[81,219],"suites,":[82],"PerfBench":[83,115,215],"features":[84],"novel":[86],"evaluation":[87,137],"harness":[88],"allows":[90],"generate":[93],"their":[94],"own":[95],"validates":[99],"fixes":[100,121],"by":[101,130,185],"comparing":[102],"execution":[103],"metrics":[104],"collected":[105],"for":[106,198,211,221],"developer":[107,120],"fix":[108],"agent":[110,152,188,206],"Each":[112],"task":[113],"is":[116],"derived":[117],"actual":[119],"linked":[122],"performance-related":[124],"issues,":[125],"which":[126,166],"then":[128],"verified":[129],"human":[131],"experts,":[132],"ensuring":[133,186],"relevance.":[135],"Our":[136],"reveals":[138],"current":[140],"state-of-the-art":[141],"coding":[142],"struggle":[144],"with":[145,149],"optimization":[147],"tasks,":[148],"baseline":[150],"OpenHands":[151],"achieving":[153],"only":[154],"\u223c":[156,175],"3%":[157],"success":[158,177],"rate":[159,178],"our":[161],"benchmark.":[162,181],"develop":[164],"OpenHands-Perf-Agent,":[165],"incorporates":[167],"performance-aware":[168],"tooling":[169,197],"instructions":[171,191],"achieves":[173],"20%":[176],"the":[180,187,205,223],"show":[183],"has":[189],"proper":[190],"its":[194],"changes":[195],"output":[200],"processing,":[201],"we":[202],"can":[203],"improve":[204],"significantly,":[208],"but":[209],"room":[210],"improvement":[212],"still":[213],"remains.":[214],"provides":[216],"set":[220],"furthering":[222],"capabilities":[224],"of":[225],"fixing":[228],"perf":[229],"issues.":[230]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}
