{"id":"https://openalex.org/W7224895600","doi":"https://doi.org/10.48550/arxiv.2610.39468","title":"Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering","display_name":"Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224895600","doi":"https://doi.org/10.48550/arxiv.2610.39468"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39468","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39468","pdf_url":"https://arxiv.org/pdf/2610.39468","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160195426","display_name":"Mohammed Nayeem Khan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Mohammed Nayeem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160213525","display_name":"K S Sarun Kumar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, K S Sarun","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":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":0.9023000001907349,"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":0.9023000001907349,"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":0.06369999796152115,"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/T12127","display_name":"Software System Performance and Reliability","score":0.010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-coding-agents","display_name":"coding agents","score":0.8859999775886536},{"id":"https://openalex.org/keywords/observability","display_name":"observability","score":0.6549999713897705},{"id":"https://openalex.org/keywords/hash-chains","display_name":"hash chains","score":0.5920000076293945},{"id":"https://openalex.org/keywords/credential-leakage","display_name":"credential leakage","score":0.42899999022483826},{"id":"https://openalex.org/keywords/tamper-detection","display_name":"tamper detection","score":0.718999981880188},{"id":"https://openalex.org/keywords/replay-verification","display_name":"replay verification","score":0.5960000157356262},{"id":"https://openalex.org/keywords/levels-of-autonomy","display_name":"autonomy levels","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103000283241272},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6739000082015991},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C2778024590","wikidata":"https://www.wikidata.org/wiki/Q2357432","display_name":"Cheating","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C129916263","wikidata":"https://www.wikidata.org/wiki/Q1141183","display_name":"Backward chaining","level":4,"score":0.2653000056743622},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39468","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39468","pdf_url":"https://arxiv.org/pdf/2610.39468","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.2610.39468","doi":"https://doi.org/10.48550/arxiv.2610.39468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39468","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39468","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39468","pdf_url":"https://arxiv.org/pdf/2610.39468","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224895600.pdf","grobid_xml":"https://content.openalex.org/works/W7224895600.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223695315","https://openalex.org/W7214962458","https://openalex.org/W7165108501","https://openalex.org/W7167644326","https://openalex.org/W7203621245","https://openalex.org/W7171926261","https://openalex.org/W7214149460","https://openalex.org/W7214638760","https://openalex.org/W7223402385","https://openalex.org/W7203694840"],"abstract_inverted_index":{"AI":[0],"coding":[1,59],"agents":[2],"now":[3],"do":[4],"long,":[5],"multi-step":[6],"and":[7,38,70,82,119,142,195,212,230,232,268,279,286],"multi-session":[8],"software":[9],"work":[10,274],"with":[11,134,283],"little":[12],"supervision.":[13],"When":[14],"a":[15,95,114,190,218,222,233,238],"developer":[16],"comes":[17],"back":[18],"to":[19,128],"that":[20,123,143,172,236],"work,":[21],"the":[22,28,139,147,168,246,249,273],"useful":[23],"question":[24],"is":[25,41,251],"not":[26],"what":[27,32],"model":[29],"said":[30],"but":[31],"was":[33],"actually":[34],"done,":[35],"by":[36],"whom,":[37],"whether":[39],"it":[40],"finished.":[42],"We":[43,271],"study":[44],"this":[45],"in":[46,156,198],"three":[47],"parts.":[48],"First,":[49],"we":[50,93,121,205],"verify":[51],"Agenttrail,":[52],"an":[53,87,214],"open-source":[54],"local":[55,89,220],"observability":[56],"tool":[57,108],"for":[58,162,228],"agents,":[60],"against":[61,275],"its":[62,83],"source":[63],"at":[64,73,262],"commit":[65],"e4ba2da:":[66],"nine":[67],"documented":[68],"constants":[69],"mechanisms":[71],"hold":[72],"file-and-line":[74],"level,":[75],"two":[76],"event":[77,216],"pipelines":[78],"are":[79],"never":[80],"unified,":[81],"Map":[84],"service":[85],"has":[86],"unauthenticated":[88],"mutation":[90],"surface.":[91],"Second,":[92],"run":[94,179],"prototype":[96],"of":[97,130,145,167,177,185,210,240,253],"our":[98,291],"system":[99],"on":[100,290],"45":[101],"real":[102],"coding-agent":[103],"sessions":[104,178,200],"(102,233":[105],"records,":[106],"20,577":[107],"executions,":[109],"2,336":[110],"human-to-agent":[111],"episodes).":[112],"With":[113],"blind-audited":[115],"classifier":[116],"(precision":[117],"83.3%":[118],"96.7%)":[120],"estimate":[122],"23.4%":[124],"(95%":[125],"CI":[126],"17.1":[127],"35.7)":[129],"code-editing":[131],"episodes":[132],"end":[133],"no":[135,154,257],"independent":[136],"check":[137],"after":[138,151],"last":[140],"edit,":[141],"57.8%":[144],"to-dos":[146],"agent":[148],"marked":[149],"complete":[150],"editing":[152],"had":[153],"proof":[155],"between.":[157],"A":[158],"10-minute":[159],"timing":[160],"heuristic":[161],"session":[163,170],"hand-offs":[164],"recovers":[165],"6":[166],"24":[169,182],"pairs":[171],"content":[173,258],"lineage":[174],"links.":[175],"42%":[176],"longer":[180],"than":[181],"hours,":[183],"48.1%":[184],"transcript":[186],"bytes":[187],"lie":[188],"past":[189],"2":[191],"MiB":[192],"replay":[193],"bound,":[194],"1,326":[196],"records":[197],"16":[199],"contain":[201],"credential-like":[202],"strings.":[203],"Third,":[204],"propose":[206],"Soei":[207],"(Structured":[208],"Observability":[209],"Evidence":[211],"Intent):":[213],"acknowledgement-aware":[215],"schema,":[217],"hash-chained":[219],"ledger,":[221],"W3C":[223],"PROV-aligned":[224],"graph,":[225],"calibrated":[226],"inference":[227],"attribution":[229],"lineage,":[231],"verification":[234],"layer":[235],"keeps":[237],"claim":[239],"completion":[241],"apart":[242],"from":[243],"proof.":[244],"On":[245],"same":[247],"corpus":[248],"ledger":[250],"20%":[252],"raw":[254],"size,":[255],"holds":[256],"or":[259],"credentials,":[260],"verifies":[261],"about":[263],"126k":[264],"events/s,":[265],"detects":[266],"tampering":[267],"replays":[269],"deterministically.":[270],"position":[272],"concurrent":[276],"2026":[277],"proposals":[278],"define":[280],"autonomy":[281],"levels":[282],"evidence":[284],"gates":[285],"harness":[287],"metrics":[288],"baselined":[289],"data.":[292]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}