{"id":"https://openalex.org/W7167021585","doi":"https://doi.org/10.48550/arxiv.2607.00151","title":"SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering","display_name":"SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7167021585","doi":"https://doi.org/10.48550/arxiv.2607.00151"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.00151","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00151","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.00151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041947969","display_name":"Zaifeng Pan","orcid":"https://orcid.org/0000-0002-6759-2616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Zaifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139883865","display_name":"Qianxu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qianxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139878581","display_name":"Zhengding Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhengding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139870245","display_name":"Chang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139890656","display_name":"Yue Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035700377","display_name":"Yanbo Zhou","orcid":"https://orcid.org/0000-0002-5347-2824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yanbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139898501","display_name":"Steven Swanson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swanson, Steven","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049726719","display_name":"Yan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yufei","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":false,"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/T12127","display_name":"Software System Performance and Reliability","score":0.1396999955177307,"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":0.1396999955177307,"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/T12203","display_name":"Mobile Agent-Based Network Management","score":0.1387999951839447,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.09669999778270721,"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/context","display_name":"Context (archaeology)","score":0.6417999863624573},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6040999889373779},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5954999923706055},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4864000082015991},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.47510001063346863},{"id":"https://openalex.org/keywords/model-transformation","display_name":"Model transformation","score":0.47360000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607000112533569},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6417999863624573},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6040999889373779},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5645999908447266},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C2779791154","wikidata":"https://www.wikidata.org/wiki/Q258040","display_name":"Model transformation","level":3,"score":0.47360000014305115},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4205000102519989},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C2778361913","wikidata":"https://www.wikidata.org/wiki/Q7248437","display_name":"Program transformation","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C84511453","wikidata":"https://www.wikidata.org/wiki/Q2914952","display_name":"Concurrency control","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.00151","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00151","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.00151","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00151","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-based":[0],"agents":[1],"execute":[2],"multi-turn":[3],"workflows":[4],"with":[5,14,159],"continuously":[6],"growing":[7],"contexts,":[8],"where":[9,75],"LLM":[10,148,180],"calls":[11],"are":[12,73],"interleaved":[13],"tool":[15],"invocations":[16],"and":[17,36,57,128,172,179,192],"environment":[18],"feedback.":[19],"To":[20],"maintain":[21],"model":[22,105],"quality,":[23],"modern":[24],"agent":[25,108,177],"frameworks":[26,109,178],"rely":[27],"on":[28,97],"context":[29,41,48,71,112,137,169],"engineering":[30,170],"strategies":[31,45,171],"such":[32],"as":[33,114],"offloading,":[34],"reduction,":[35],"isolation":[37],"to":[38,61,90,110,151,166,197],"control":[39],"the":[40,76],"length.":[42],"However,":[43],"these":[44,126,153],"introduce":[46],"significant":[47],"transformation":[49,52,77,190],"overhead:":[50],"each":[51],"invalidates":[53],"existing":[54,176],"KV":[55,131],"caches":[56,132],"triggers":[58],"re-prefill,":[59],"leading":[60],"increased":[62],"time-to-first-token":[63],"(TTFT).":[64],"In":[65],"this":[66,98],"paper,":[67],"we":[68,100],"identify":[69],"that":[70,106,185],"transformations":[72,89,113,127],"segment-decomposable,":[74],"of":[78,83,94],"a":[79,102,144],"prefix":[80],"is":[81],"independent":[82],"future":[84],"tokens.":[85],"This":[86],"property":[87],"enables":[88],"be":[91],"executed":[92],"ahead":[93],"time.":[95],"Based":[96],"insight,":[99],"propose":[101],"lookahead":[103],"programming":[104],"allows":[107],"express":[111],"asynchronous":[115,154],"operations":[116],"without":[117,139],"modifying":[118],"their":[119],"execution":[120],"logic.":[121],"The":[122],"runtime":[123],"proactively":[124],"executes":[125],"prepares":[129],"transformed":[130],"in":[133,147],"advance,":[134],"enabling":[135],"direct":[136],"replacement":[138],"blocking.":[140],"We":[141,162],"further":[142],"design":[143],"lookahead-aware":[145],"scheduler":[146],"serving":[149,181],"systems":[150],"support":[152,167],"requests":[155],"alongside":[156],"latency-critical":[157],"workloads":[158],"controlled":[160],"interference.":[161],"implement":[163],"our":[164,186],"approach":[165,187],"representative":[168],"integrate":[173],"it":[174],"into":[175],"systems.":[182],"Experiments":[183],"show":[184],"effectively":[188],"eliminates":[189],"overhead":[191],"reduces":[193],"TTFT":[194],"by":[195],"up":[196],"11.9x.":[198]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}
