{"id":"https://openalex.org/W7224296154","doi":"https://doi.org/10.18653/2026.emnlp-demos.37","title":"TraceForge: A Human-Gated System for Auto-Hardening Tool-Using LLM Agents into Immutable Workflow DAGs","display_name":"TraceForge: A Human-Gated System for Auto-Hardening Tool-Using LLM Agents into Immutable Workflow DAGs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224296154","doi":"https://doi.org/10.18653/2026.emnlp-demos.37"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-demos.37","doi":"https://doi.org/10.18653/2026.emnlp-demos.37","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-demos.37","pdf_url":"https://aclanthology.org/2026.emnlp-demos.37.pdf","source":{"id":"https://openalex.org/S7407087688","display_name":"Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)","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":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-demos.37.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075371849","display_name":"Santhiya Rajan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210120949","display_name":"Multiverse Computing (Spain)","ror":"https://ror.org/02p1vs657","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210120949"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Santhiya Rajan","raw_affiliation_strings":["Multiverse Computing , Paseo de Miram\u00f3n 170 , 20014 Donostia / San Sebasti\u00e1n , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multiverse Computing , Paseo de Miram\u00f3n 170 , 20014 Donostia / San Sebasti\u00e1n , Spain","institution_ids":["https://openalex.org/I4210120949"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075371849"],"corresponding_institution_ids":["https://openalex.org/I4210120949"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86906804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.3540000021457672,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.3540000021457672,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.17569999396800995,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10939999669790268,"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/multi-agent-orchestration","display_name":"multi-agent orchestration","score":0.6589999794960022},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.5049999952316284},{"id":"https://openalex.org/keywords/on-premises-deployment","display_name":"on-premise deployment","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6266999840736389},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.24940000474452972}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-demos.37","doi":"https://doi.org/10.18653/2026.emnlp-demos.37","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-demos.37","pdf_url":"https://aclanthology.org/2026.emnlp-demos.37.pdf","source":{"id":"https://openalex.org/S7407087688","display_name":"Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)","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":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-demos.37","doi":"https://doi.org/10.18653/2026.emnlp-demos.37","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-demos.37","pdf_url":"https://aclanthology.org/2026.emnlp-demos.37.pdf","source":{"id":"https://openalex.org/S7407087688","display_name":"Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)","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":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224296154.pdf","grobid_xml":"https://content.openalex.org/works/W7224296154.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4378505261","https://openalex.org/W4385474529","https://openalex.org/W4385965642","https://openalex.org/W4403622204","https://openalex.org/W4415795271","https://openalex.org/W7126224343","https://openalex.org/W7162804409","https://openalex.org/W7166047539","https://openalex.org/W7167825536","https://openalex.org/W7172499856"],"related_works":["https://openalex.org/W7224016010","https://openalex.org/W7140134021","https://openalex.org/W7224232570","https://openalex.org/W7224256007","https://openalex.org/W7224613519","https://openalex.org/W7111328634","https://openalex.org/W7166876662","https://openalex.org/W7167596465","https://openalex.org/W7203976842","https://openalex.org/W7163822186"],"abstract_inverted_index":{"Tool-using":[0],"language":[1],"agents":[2],"are":[3,20],"flexible":[4],"but":[5],"nondeterministic:":[6],"an":[7,26,32,56],"orchestrator":[8],"LLM":[9],"re-plans":[10],"on":[11,40],"every":[12,134],"request,":[13,42],"adding":[14],"latency,":[15],"cost,":[16],"and":[17,68,89,102,110,137,152],"paths":[18],"that":[19,29,94],"hard":[21],"to":[22,52,107],"audit.We":[23],"demonstrate":[24],"Trace-Forge,":[25],"on-premise":[27],"system":[28],"observes":[30],"how":[31],"agent":[33,57],"actually":[34],"solves":[35],"a":[36,46,70,73,78,85,90,96,146],"recurring":[37],"task":[38],"and,":[39],"operator":[41],"hardens":[43],"it":[44],"into":[45],"deterministic,":[47],"immutable":[48,98],"workflow":[49],"DAG.Trace-Forge":[50],"attaches":[51],"the":[53,127,157],"OpenTelemetry":[54],"traces":[55],"already":[58],"emits":[59],"(zero":[60],"code":[61],"changes),":[62],"reconstructs":[63],"each":[64],"run's":[65],"execution":[66],"DAG,":[67],"runs":[69,83],"human-gated":[71],"loop:":[72],"statistical":[74],"aggregation":[75],"gate":[76,93],"(proposes":[77],"DAG":[79],"only":[80],"once":[81],"enough":[82],"agree),":[84],"Judge-LLM":[86],"reflection":[87],"step,":[88],"human":[91],"freeze":[92],"writes":[95],"versioned,":[97],"specification":[99],"with":[100,118,149],"lineage":[101],"rollback.The":[103],"pipeline":[104],"is":[105,143,153],"topology-agnostic-applied":[106],"single-agent":[108],"tool-callers":[109],"multi-agent":[111],"orchestrators":[112],"alike-and":[113],"all":[114],"components":[115],"run":[116],"onpremise":[117],"no":[119,150],"external":[120],"dependencies.On":[121],"held-out":[122],"requests,":[123],"frozen":[124],"workflows":[125],"reproduce":[126],"dynamic":[128],"agent's":[129],"outputs":[130],"exactly":[131],"while":[132],"removing":[133],"planner-LLM":[135],"call":[136],"cutting":[138],"latency":[139],"1.39\u00d7.The":[140],"entire":[141],"loop":[142],"driven":[144],"from":[145],"browser":[147],"console":[148],"coding,":[151],"shown":[154],"end-to-end":[155],"in":[156],"accompanying":[158],"screencast.":[159]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-30T00:00:00"}