{"id":"https://openalex.org/W7162787177","doi":"https://doi.org/10.1145/3745756.3809203","title":"TimelyLLM: Time-sensitive LLM Serving System for Physical-I/O Limited Agents","display_name":"TimelyLLM: Time-sensitive LLM Serving System for Physical-I/O Limited Agents","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162787177","doi":"https://doi.org/10.1145/3745756.3809203"},"language":null,"primary_location":{"id":"doi:10.1145/3745756.3809203","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809203","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3745756.3809203","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049748462","display_name":"Neiwen Ling","orcid":"https://orcid.org/0000-0003-2072-1502"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neiwen Ling","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0003-2072-1502","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137397723","display_name":"Guojun Chen","orcid":"https://orcid.org/0009-0001-6450-4983"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guojun Chen","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0009-0001-6450-4983","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031018906","display_name":"Anurag Khandelwal","orcid":"https://orcid.org/0000-0002-2199-6391"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Khandelwal","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0002-2199-6391","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137359452","display_name":"Lin Zhong","orcid":"https://orcid.org/0000-0003-0840-167X"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Zhong","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0003-0840-167X","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87271966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.26579999923706055,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.26579999923706055,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09870000183582306,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.0658000037074089,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.661300003528595},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.503600001335144},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44440001249313354},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.32580000162124634},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.32440000772476196},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3197999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098999857902527},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.661300003528595},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4399999976158142},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3745756.3809203","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809203","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3745756.3809203","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809203","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8377316191","display_name":null,"funder_award_id":"2112562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2020953065","https://openalex.org/W4387321091","https://openalex.org/W4389519291","https://openalex.org/W4393178509","https://openalex.org/W4412875469","https://openalex.org/W4413240314","https://openalex.org/W4414735925"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"integrated":[6],"into":[7],"Physical-I/O":[8],"limited":[9],"agents,":[10,47],"such":[11],"as":[12],"robots":[13],"and":[14,40,52,62,103,115,120,156,171],"voice":[15],"assistants,":[16],"which":[17],"execute":[18],"outputs":[19],"sequentially.":[20],"However,":[21],"existing":[22],"LLM":[23,37,89,135],"serving":[24,136,147],"systems":[25],"typically":[26],"employ":[27],"a":[28,82,99,133,141],"throughput-oriented":[29],"batching":[30],"mechanism,":[31,105],"ignoring":[32],"the":[33,41,65,92,108,165,173],"large":[34],"gap":[35,110],"between":[36,111],"generation":[38,90,102,114],"speed":[39],"constrained":[42],"physical":[43,93],"I/O":[44],"rates":[45],"of":[46,68,95,132],"thus":[48],"wasting":[49],"execution":[50,66,116],"slack":[51],"worsening":[53],"resource":[54],"contention.":[55],"Besides,":[56],"they":[57],"treat":[58],"all":[59],"tokens":[60],"equally":[61],"cannot":[63],"anticipate":[64],"implications":[67],"different":[69],"content,":[70],"preventing":[71],"scheduling":[72,104],"aligned":[73],"with":[74,91],"agent-side":[75],"behavior.":[76],"To":[77],"address":[78],"it,":[79],"we":[80],"propose":[81],"new":[83],"system":[84,144],"named":[85],"TimelyLLM":[86,97,129,163],"that":[87,162],"coordinates":[88],"behavior":[94],"agents.":[96],"introduces":[98],"novel":[100],"segmented":[101],"strategically":[106],"leveraging":[107],"time":[109,166,176],"agent":[112],"plan":[113],"to":[117,145,169],"reduce":[118],"contention":[119],"improve":[121],"response":[122],"latency":[123],"under":[124],"multi-agent":[125],"workloads.":[126],"We":[127,138],"implement":[128],"on":[130],"top":[131],"widely-used":[134],"framework.":[137],"also":[139],"build":[140],"dataset":[142],"collection":[143],"construct":[146],"workloads":[148],"from":[149],"real-world":[150],"robots,":[151],"including":[152],"drones,":[153],"robot":[154],"arms,":[155],"quadruped":[157],"robots.":[158],"Our":[159],"evaluation":[160],"demonstrates":[161],"improves":[164],"utility":[167],"up":[168],"1.52\u00d7,":[170],"reduces":[172],"overall":[174],"waiting":[175],"by":[177],"84%.":[178]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}