{"id":"https://openalex.org/W4414109772","doi":"https://doi.org/10.1145/3744969.3748425","title":"Continual Benchmarking of LLM-Based Systems on Networking Operations","display_name":"Continual Benchmarking of LLM-Based Systems on Networking Operations","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4414109772","doi":"https://doi.org/10.1145/3744969.3748425"},"language":"en","primary_location":{"id":"doi:10.1145/3744969.3748425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744969.3748425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3744969.3748425","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 SIGCOMM 2025 Posters and Demos","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3744969.3748425","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119586846","display_name":"Ioannis Protogeros","orcid":"https://orcid.org/0009-0005-3840-7425"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Ioannis Protogeros","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":"https://orcid.org/0009-0005-3840-7425","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070110259","display_name":"Laurent Vanbever","orcid":"https://orcid.org/0000-0003-1455-4381"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Laurent Vanbever","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":"https://orcid.org/0000-0003-1455-4381","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119586846"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24474187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11125","display_name":"Petri Nets in System Modeling","score":0.9724000096321106,"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"}},"topics":[{"id":"https://openalex.org/T11125","display_name":"Petri Nets in System Modeling","score":0.9724000096321106,"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/benchmarking","display_name":"Benchmarking","score":0.925599992275238},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.72079998254776},{"id":"https://openalex.org/keywords/complexity-management","display_name":"Complexity management","score":0.38260000944137573},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.314300000667572},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.30550000071525574},{"id":"https://openalex.org/keywords/best-practice","display_name":"Best practice","score":0.3028999865055084}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.925599992275238},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.72079998254776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6352999806404114},{"id":"https://openalex.org/C57936825","wikidata":"https://www.wikidata.org/wiki/Q1780925","display_name":"Complexity management","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C129763632","wikidata":"https://www.wikidata.org/wiki/Q1454667","display_name":"Network management","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27709999680519104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2648000121116638}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744969.3748425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744969.3748425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3744969.3748425","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 SIGCOMM 2025 Posters and Demos","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3744969.3748425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744969.3748425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3744969.3748425","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 SIGCOMM 2025 Posters and Demos","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414109772.pdf","grobid_xml":"https://content.openalex.org/works/W4414109772.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W4388625574","https://openalex.org/W4388629245","https://openalex.org/W4405022259"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"The":[0],"inherent":[1],"complexity":[2,72],"of":[3,27,34,73],"operating":[4],"modern":[5],"network":[6,21],"infrastructures":[7],"has":[8],"led":[9],"to":[10,19],"growing":[11],"interest":[12],"in":[13,24,43,77],"using":[14],"Large":[15],"Language":[16],"Models":[17],"(LLMs)":[18],"support":[20],"operators,":[22],"particularly":[23],"the":[25,32,69],"area":[26],"Incident":[28],"Management":[29],"(IM).":[30],"Yet,":[31],"absence":[33],"standardized":[35],"benchmarks":[36],"for":[37,62],"evaluating":[38],"such":[39],"systems":[40],"poses":[41],"challenges":[42],"tracking":[44],"progress,":[45],"comparing":[46],"approaches,":[47],"and":[48,71],"uncovering":[49],"their":[50],"limitations.":[51],"As":[52],"LLM-based":[53],"tools":[54],"become":[55],"widespread,":[56],"there":[57],"is":[58],"a":[59,63],"clear":[60],"need":[61],"comprehensive":[64],"benchmarking":[65],"suite":[66],"that":[67],"reflects":[68],"diversity":[70],"operational":[74],"tasks":[75],"encountered":[76],"real-world":[78],"networks.":[79]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
