{"id":"https://openalex.org/W7208838801","doi":null,"title":"RASER: Resilient Agent Scheduling and Execution Runtime for HPC Clusters","display_name":"RASER: Resilient Agent Scheduling and Execution Runtime for HPC Clusters","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208838801"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.03598","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03598","pdf_url":"https://arxiv.org/pdf/2609.03598","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.03598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088013696","display_name":"Sima Attar-Khorasani","orcid":"https://orcid.org/0000-0002-7396-1983","observed_orcids":["https://orcid.org/0000-0002-7396-1983"]},"institutions":[{"id":"https://openalex.org/I4405278470","display_name":"Center for Information Services and High Performance Computing","ror":"https://ror.org/003kzqz52","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4405272610","https://openalex.org/I4405278470","https://openalex.org/I78650965"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Attar-Khorasani, Sima","raw_affiliation_strings":["Center for Information Services and High Performance Computing (ZIH )","TUD Dresden University of Technology , Dresden , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information Services and High Performance Computing (ZIH )","institution_ids":["https://openalex.org/I4405278470"]},{"raw_affiliation_string":"TUD Dresden University of Technology , Dresden , Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054704630","display_name":"Matthias Lieber","orcid":"https://orcid.org/0000-0003-3137-0648","observed_orcids":["https://orcid.org/0000-0003-3137-0648"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lieber, Matthias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081540847","display_name":"Siavash Ghiasvand","orcid":"https://orcid.org/0000-0001-6627-0159","observed_orcids":["https://orcid.org/0000-0001-6627-0159"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghiasvand, Siavash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9682999849319458,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9682999849319458,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.009100000374019146,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/agent-scheduling","display_name":"agent scheduling","score":0.753000020980835},{"id":"https://openalex.org/keywords/agentic-workflows","display_name":"agentic workflows","score":0.8349999785423279},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7580000162124634},{"id":"https://openalex.org/keywords/hpc-job-scheduling","display_name":"HPC job scheduling","score":0.7979999780654907},{"id":"https://openalex.org/keywords/slurm","display_name":"SLURM","score":0.8040000200271606},{"id":"https://openalex.org/keywords/work-stealing","display_name":"work stealing","score":0.9940000176429749},{"id":"https://openalex.org/keywords/checkpointing","display_name":"checkpointing","score":0.7900000214576721},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.7080000042915344},{"id":"https://openalex.org/keywords/apptainer","display_name":"Apptainer","score":0.8240000009536743},{"id":"https://openalex.org/keywords/container-isolation","display_name":"container isolation","score":0.8479999899864197},{"id":"https://openalex.org/keywords/makespan-minimization","display_name":"makespan minimization","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518999814987183},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7034000158309937},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6115999817848206},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C206952183","wikidata":"https://www.wikidata.org/wiki/Q1193100","display_name":"Preemption","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C72108876","wikidata":"https://www.wikidata.org/wiki/Q844565","display_name":"Transaction processing","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C112904061","wikidata":"https://www.wikidata.org/wiki/Q1077480","display_name":"Hypervisor","level":4,"score":0.2705000042915344},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.03598","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03598","pdf_url":"https://arxiv.org/pdf/2609.03598","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.03598","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03598","pdf_url":"https://arxiv.org/pdf/2609.03598","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208838801.pdf","grobid_xml":"https://content.openalex.org/works/W7208838801.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W2139244298","https://openalex.org/W2290712622","https://openalex.org/W2527672088","https://openalex.org/W2613409207","https://openalex.org/W2735218636","https://openalex.org/W2768885587","https://openalex.org/W2943761765","https://openalex.org/W2974562547","https://openalex.org/W4315647220","https://openalex.org/W4388581162","https://openalex.org/W7166009806"],"related_works":["https://openalex.org/W7212073386","https://openalex.org/W7168268652","https://openalex.org/W4417510046","https://openalex.org/W7163925273","https://openalex.org/W7170030991","https://openalex.org/W3176930059","https://openalex.org/W4285327190","https://openalex.org/W4411175213","https://openalex.org/W7223296064","https://openalex.org/W7196948702"],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,66,80],"modern":[3,67],"agents":[4],"powered":[5],"by":[6,55,87,129],"large":[7],"language":[8],"models":[9],"has":[10],"created":[11],"a":[12,73],"demand":[13],"for":[14,36,50,167],"executing":[15],"long-horizon,":[16],"autonomous":[17],"workflows":[18,53,82,170],"in":[19],"various":[20],"domains":[21],"that":[22,76,125],"require":[23],"significant":[24],"computational":[25],"resources.":[26],"While":[27],"High":[28],"Performance":[29],"Computing":[30],"clusters":[31,86],"provide":[32],"the":[33],"ideal":[34],"infrastructure":[35],"these":[37],"computation-intensive":[38],"workloads,":[39],"traditional":[40],"HPC":[41,85,173],"job":[42,95],"schedulers":[43],"such":[44],"as":[45],"Slurm":[46,112],"are":[47],"not":[48],"designed":[49],"dynamic,":[51],"agentic":[52,81,94,169],"characterized":[54],"unpredictable":[56],"task":[57],"durations,":[58],"external":[59,159],"API":[60],"calls,":[61],"and":[62,114,146],"fault":[63],"tolerance":[64],"requirements":[65],"agents.":[68],"This":[69],"work":[70,98],"presents":[71],"RASER,":[72],"user-space":[74,104],"framework":[75],"enables":[77],"seamless":[78],"execution":[79],"on":[83,171],"production":[84],"extending":[88],"Slurm's":[89],"internal":[90],"primitives.":[91],"RASER":[92,126,141],"introduces":[93],"arrays":[96],"with":[97,111],"stealing":[99],"via":[100],"shared":[101],"filesystem":[102],"queues,":[103],"checkpointing":[105],"through":[106],"application-level":[107],"state":[108],"serialization":[109],"combined":[110],"requeue,":[113],"Apptainer":[115],"container-based":[116],"isolation":[117],"without":[118],"requiring":[119],"any":[120],"image":[121],"modifications.":[122],"Evaluations":[123],"demonstrate":[124],"reduces":[127],"makespan":[128],"nearly":[130],"39%":[131],"compared":[132],"to":[133],"static":[134],"partitioning":[135],"while":[136,148],"achieving":[137],"near-full":[138],"CPU":[139],"utilization.":[140],"provides":[142],"resilience":[143],"against":[144],"preemption":[145],"failures":[147],"maintaining":[149],"minimal":[150],"checkpoint/restore":[151],"overhead.":[152],"It":[153],"requires":[154],"no":[155],"kernel":[156],"privileges":[157],"or":[158],"database":[160],"infrastructure,":[161],"making":[162],"it":[163],"an":[164],"accessible":[165],"solution":[166],"deploying":[168],"existing":[172],"infrastructure.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-06T00:00:00"}
