{"id":"https://openalex.org/W7162109212","doi":"https://doi.org/10.1145/3786335.3813230","title":"Goal-Oriented Reliability and Self-Improvement for Multi-Agent Systems","display_name":"Goal-Oriented Reliability and Self-Improvement for Multi-Agent Systems","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162109212","doi":"https://doi.org/10.1145/3786335.3813230"},"language":null,"primary_location":{"id":"doi:10.1145/3786335.3813230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813230","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786335.3813230","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136744781","display_name":"Vishwanath Katharki","orcid":"https://orcid.org/0009-0007-2576-7186"},"institutions":[{"id":"https://openalex.org/I131328143","display_name":"Union Bank of Switzerland","ror":"https://ror.org/01ekk8h85","country_code":"CH","type":"funder","lineage":["https://openalex.org/I131328143"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vishwanath Katharki","raw_affiliation_strings":["SaraLabs, San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0007-2576-7186","affiliations":[{"raw_affiliation_string":"SaraLabs, San Jose, USA","institution_ids":["https://openalex.org/I131328143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112842550","display_name":"Sainyam Galhotra","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sainyam Galhotra","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0003-2529-4036","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1367","last_page":"1371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.4325999915599823,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.4325999915599823,"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/T12127","display_name":"Software System Performance and Reliability","score":0.39329999685287476,"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/T10142","display_name":"Formal Methods in Verification","score":0.024900000542402267,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reliability","display_name":"Reliability (semiconductor)","score":0.6639999747276306},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.46779999136924744},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4595000147819519},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4406999945640564},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4228000044822693},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.41440001130104065},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.3921000063419342},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3880999982357025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555999755859375},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6639999747276306},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.46779999136924744},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4406999945640564},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.41440001130104065},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C202973057","wikidata":"https://www.wikidata.org/wiki/Q7380130","display_name":"Runtime verification","level":3,"score":0.37619999051094055},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C200749887","wikidata":"https://www.wikidata.org/wiki/Q1165574","display_name":"System monitoring","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.335999995470047},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C66283442","wikidata":"https://www.wikidata.org/wiki/Q1389268","display_name":"Failure mode and effects analysis","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C33054407","wikidata":"https://www.wikidata.org/wiki/Q6504747","display_name":"Software verification","level":5,"score":0.25870001316070557},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786335.3813230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813230","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786335.3813230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813230","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2145071552","https://openalex.org/W2257979135","https://openalex.org/W4388626886","https://openalex.org/W4393160747","https://openalex.org/W4412887039","https://openalex.org/W4417200309","https://openalex.org/W7133202489"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1,90],"a":[2,45,58,73,91,96,106],"runtime":[3],"reliability":[4,113],"and":[5,34,67,71,81,104,114,134],"self-improvement":[6],"framework":[7],"for":[8,32],"multi-agent":[9,97],"AI":[10],"systems.":[11],"Modern":[12],"agentic":[13],"pipelines":[14],"frequently":[15],"degrade":[16],"when":[17,118],"task":[18],"distributions":[19],"change,":[20],"tools":[21],"fail,":[22],"or":[23],"prompts":[24],"drift,":[25],"yet":[26],"existing":[27],"frameworks":[28],"provide":[29],"limited":[30],"support":[31],"diagnosing":[33],"correcting":[35],"these":[36],"failures.":[37],"Our":[38],"system":[39,100,110,117,126],"introduces":[40],"three":[41],"core":[42],"components:":[43],"(1)":[44],"Goal":[46],"Decomposition":[47],"Engine":[48],"(GDE)":[49],"that":[50,63,77],"translates":[51],"high-level":[52],"objectives":[53],"into":[54],"verifiable":[55],"sub-goals,":[56],"(2)":[57],"Runtime":[59],"Reliability":[60],"Monitor":[61],"(RRM)":[62],"tracks":[64],"agent":[65,136],"execution":[66,79],"detects":[68],"goal-level":[69],"degradation,":[70],"(3)":[72],"Self-Improvement":[74],"Loop":[75],"(SIL)":[76],"analyzes":[78],"traces":[80],"automatically":[82],"proposes":[83],"policy":[84],"updates.":[85],"In":[86],"this":[87],"demonstration":[88],"we":[89],"live":[92],"end-to-end":[93],"scenario":[94],"where":[95],"software":[98],"engineering":[99],"plans,":[101],"implements,":[102],"tests,":[103],"deploys":[105],"microservice":[107],"while":[108],"our":[109,125],"continuously":[111],"monitors":[112],"adapts":[115],"the":[116,140],"failures":[119],"occur.":[120],"Attendees":[121],"will":[122],"observe":[123],"how":[124],"identifies":[127],"failure":[128],"points,":[129],"generates":[130],"new":[131],"evaluation":[132],"scenarios,":[133],"improves":[135],"performance":[137],"without":[138],"retraining":[139],"underlying":[141],"models.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-23T00:00:00"}
