{"id":"https://openalex.org/W7125908856","doi":"https://doi.org/10.1109/ase63991.2025.00067","title":"Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents","display_name":"Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7125908856","doi":"https://doi.org/10.1109/ase63991.2025.00067"},"language":"en","primary_location":{"id":"doi:10.1109/ase63991.2025.00067","doi":"https://doi.org/10.1109/ase63991.2025.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00067","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.03455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103181376","display_name":"Benjamin Rombaut","orcid":"https://orcid.org/0000-0001-5947-2684","observed_orcids":["https://orcid.org/0000-0001-5947-2684"]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Benjamin Rombaut","raw_affiliation_strings":["Centre for Software Excellence,Huawei,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Software Excellence,Huawei,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028220736","display_name":"Sogol Masoumzadeh","orcid":"https://orcid.org/0000-0003-3639-194X","observed_orcids":["https://orcid.org/0000-0003-3639-194X"]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sogol Masoumzadeh","raw_affiliation_strings":["Centre for Software Excellence,Huawei,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Software Excellence,Huawei,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114638172","display_name":"Kirill Vasilevski","orcid":"https://orcid.org/0009-0006-0292-4970","observed_orcids":["https://orcid.org/0009-0006-0292-4970"]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kirill Vasilevski","raw_affiliation_strings":["Centre for Software Excellence,Huawei,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Software Excellence,Huawei,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079401267","display_name":"Dayi Lin","orcid":"https://orcid.org/0000-0002-4034-6650","observed_orcids":["https://orcid.org/0000-0002-4034-6650"]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dayi Lin","raw_affiliation_strings":["Centre for Software Excellence,Huawei,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Software Excellence,Huawei,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513","observed_orcids":["https://orcid.org/0000-0001-7749-5513"]},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["Queen&#x2019;s University,Kingston,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen&#x2019;s University,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.2321,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.99127719,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"739","last_page":"751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.5189999938011169,"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":0.5189999938011169,"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":0.26249998807907104,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.11699999868869781,"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/automated-debugging","display_name":"automated debugging","score":0.4790000021457672},{"id":"https://openalex.org/keywords/automated-correction","display_name":"automated correction","score":0.6570000052452087},{"id":"https://openalex.org/keywords/software-engineering-agents","display_name":"software engineering agents","score":0.45899999141693115},{"id":"https://openalex.org/keywords/openhands","display_name":"OpenHands","score":0.48100000619888306},{"id":"https://openalex.org/keywords/mmlu","display_name":"MMLU","score":0.6800000071525574},{"id":"https://openalex.org/keywords/agent-transparency","display_name":"agent transparency","score":0.4950000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196000218391418},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.4059000015258789},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C2776608531","wikidata":"https://www.wikidata.org/wiki/Q12253","display_name":"Watson","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3043000102043152},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25099998712539673},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ase63991.2025.00067","doi":"https://doi.org/10.1109/ase63991.2025.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00067","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.03455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.03455","pdf_url":"https://arxiv.org/pdf/2411.03455","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.03455","doi":"https://doi.org/10.48550/arxiv.2411.03455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.03455","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:2411.03455","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.03455","pdf_url":"https://arxiv.org/pdf/2411.03455","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/W7125908856.pdf","grobid_xml":"https://content.openalex.org/works/W7125908856.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W3015177564","https://openalex.org/W3216137074","https://openalex.org/W4220914596","https://openalex.org/W4391136507","https://openalex.org/W4394744510","https://openalex.org/W4400484650","https://openalex.org/W4402442868","https://openalex.org/W7125007218"],"related_works":["https://openalex.org/W4414688275","https://openalex.org/W7128697492","https://openalex.org/W6910948070","https://openalex.org/W7169214643","https://openalex.org/W7125909867","https://openalex.org/W7125905084","https://openalex.org/W7220661454","https://openalex.org/W7167425705","https://openalex.org/W7129289796","https://openalex.org/W7213419565"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"integrated":[6],"into":[7],"autonomous":[8],"systems,":[9],"giving":[10],"rise":[11],"to":[12,66],"a":[13,79],"new":[14],"class":[15],"of":[16,62,87],"software":[17,32,52],"known":[18],"as":[19,31],"Agentware,":[20],"where":[21],"LLM-powered":[22],"agents":[23,90,124],"perform":[24],"complex,":[25],"open-ended":[26],"tasks":[27],"in":[28,107,153],"domains":[29],"such":[30],"engineering,":[33],"customer":[34],"service,":[35],"and":[36,43,68,111,119,122,132,140,151],"data":[37],"analysis.":[38],"However,":[39],"their":[40,93],"high":[41],"autonomy":[42],"opaque":[44],"reasoning":[45,72,85,98,138],"processes":[46,86],"pose":[47],"significant":[48],"challenges":[49],"for":[50,82,148],"traditional":[51],"observability":[53],"methods.":[54],"To":[55],"address":[56],"this,":[57],"we":[58],"introduce":[59],"the":[60,70,84,116,120,126],"concept":[61],"cognitive":[63],"observability\u2014the":[64],"ability":[65],"recover":[67],"inspect":[69],"implicit":[71],"behind":[73],"agent":[74],"decisions.":[75],"We":[76,104],"present":[77],"Watson,":[78],"general-purpose":[80],"framework":[81],"observing":[83],"fast-thinking":[88],"LLM":[89],"without":[91],"altering":[92],"behavior.":[94],"Watson":[95,106,135],"retroactively":[96],"infers":[97],"traces":[99],"using":[100],"prompt":[101],"attribution":[102],"techniques.":[103],"evaluate":[105],"both":[108,130],"manual":[109],"debugging":[110],"automated":[112],"correction":[113],"scenarios":[114],"across":[115],"MMLU":[117],"benchmark":[118],"AutoCodeRover":[121],"OpenHands":[123],"on":[125],"SWE-bench-lite":[127],"dataset.":[128],"In":[129],"static":[131],"dynamic":[133],"settings,":[134],"surfaces":[136],"actionable":[137],"insights":[139],"supports":[141],"targeted":[142],"interventions,":[143],"demonstrating":[144],"its":[145],"practical":[146],"utility":[147],"improving":[149],"transparency":[150],"reliability":[152],"Agentware":[154],"systems.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-29T00:00:00"}
