{"id":"https://openalex.org/W7161691160","doi":"https://doi.org/10.48550/arxiv.2605.16790","title":"TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition","display_name":"TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition","publication_year":2026,"publication_date":"2026-05-16","ids":{"openalex":"https://openalex.org/W7161691160","doi":"https://doi.org/10.48550/arxiv.2605.16790"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.16790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136466962","display_name":"Anay Kulkarni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kulkarni, Anay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136496303","display_name":"ChiaEn Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, ChiaEn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931351","display_name":"Dheeraj Mekala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mekala, Dheeraj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136476827","display_name":"Jayanth Srinivasa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasa, Jayanth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136476539","display_name":"Gaowen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Gaowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136484910","display_name":"Jingbo Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Jingbo","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/T10260","display_name":"Software Engineering Research","score":0.5579000115394592,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.5579000115394592,"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"}},{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.10859999805688858,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0364999994635582,"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/limiting","display_name":"Limiting","score":0.5796999931335449},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.542900025844574},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5241000056266785},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46399998664855957},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.37459999322891235},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087999820709229},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.542900025844574},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.16790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool":[0],"use":[1],"enables":[2],"large":[3],"language":[4],"models":[5],"to":[6,21,23,106,116,129],"solve":[7],"complex":[8],"tasks":[9],"through":[10],"sequences":[11],"of":[12,93,96,168],"API":[13],"calls,":[14],"yet":[15],"existing":[16],"reinforcement":[17],"learning":[18],"approaches":[19],"fail":[20],"scale":[22],"multi-step":[24],"composition":[25],"settings.":[26],"Outcome-based":[27],"rewards":[28,35,140],"provide":[29],"only":[30],"sparse":[31],"feedback,":[32],"while":[33],"trajectory-supervised":[34,139],"depend":[36],"on":[37,149],"annotated":[38],"reference":[39,69],"solutions,":[40],"penalizing":[41],"valid":[42,103],"alternatives":[43],"and":[44,63,81,114,154],"limiting":[45],"scalability.":[46],"We":[47,144],"propose":[48],"TIER:":[49],"Trajectory-Invariant":[50],"Execution":[51],"Rewards,":[52],"a":[53,122],"reward":[54,72,161],"framework":[55],"that":[56,159],"derives":[57],"supervision":[58,170],"directly":[59],"from":[60,68,90],"function":[61],"schemas":[62],"runtime":[64],"execution,":[65],"rather":[66],"than":[67],"trajectories.":[70],"The":[71],"decomposes":[73],"into":[74],"format":[75],"validity,":[76],"schema":[77],"adherence,":[78],"execution":[79,104],"success,":[80],"answer":[82],"correctness,":[83],"providing":[84],"dense,":[85],"interpretable":[86],"sequence-level":[87],"feedback":[88],"derived":[89],"fine-grained":[91],"verification":[92],"individual":[94],"steps":[95],"tool":[97,118],"use.":[98],"This":[99],"design":[100],"allows":[101],"any":[102],"path":[105],"receive":[107],"credit,":[108],"naturally":[109],"supporting":[110],"multiple":[111],"solution":[112],"strategies":[113],"adapting":[115],"evolving":[117],"interfaces.":[119],"On":[120],"DepthBench,":[121],"compositional":[123,172],"benchmark":[124],"stratified":[125],"by":[126],"depth":[127],"(1":[128],"6":[130],"steps),":[131],"TIER":[132],"achieves":[133],">90%":[134],"accuracy":[135],"across":[136],"steps,":[137],"where":[138],"collapse":[141],"beyond":[142],"step-4.":[143],"further":[145],"demonstrate":[146],"consistent":[147],"gains":[148],"benchmarks":[150],"like":[151],"BFCL":[152],"v3":[153],"NestFUL.":[155],"Ablation":[156],"studies":[157],"confirm":[158],"all":[160],"components":[162],"are":[163],"necessary,":[164],"highlighting":[165],"the":[166],"importance":[167],"multi-level":[169],"for":[171],"reasoning.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}