{"id":"https://openalex.org/W7136769650","doi":"https://doi.org/10.48550/arxiv.2603.12634","title":"Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents","display_name":"Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7136769650","doi":"https://doi.org/10.48550/arxiv.2603.12634"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.12634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12634","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":null,"license_id":null,"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.2603.12634","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129450645","display_name":"Yushu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yushu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129538338","display_name":"Wenlong Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Wenlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026120799","display_name":"Jiatao Li","orcid":"https://orcid.org/0009-0003-4125-3493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiajin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129492132","display_name":"Xiaoxiao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaoxiao","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/T10181","display_name":"Natural Language Processing Techniques","score":0.17170000076293945,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.17170000076293945,"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":0.08209999650716782,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.06419999897480011,"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/pruning","display_name":"Pruning","score":0.6266999840736389},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5824999809265137},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5350000262260437},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.498199999332428},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41769999265670776},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3970000147819519},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.39469999074935913},{"id":"https://openalex.org/keywords/budget-constraint","display_name":"Budget constraint","score":0.3896999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652400016784668},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.460999995470047},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C201236551","wikidata":"https://www.wikidata.org/wiki/Q7310809","display_name":"Relative value","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.12634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12634","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.12634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12634","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47103479504585266,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Test-time":[0],"scaling":[1,100],"has":[2],"become":[3],"a":[4,59,68,78,86,98,106,130,155,163],"dominant":[5],"paradigm":[6],"for":[7],"improving":[8],"LLM":[9,80,126],"agent":[10],"reliability,":[11],"yet":[12],"current":[13],"approaches":[14],"treat":[15],"compute":[16,219],"as":[17,67,97,116],"an":[18,172],"abundant":[19],"resource,":[20],"allowing":[21],"agents":[22],"to":[23,113],"exhaust":[24],"token":[25],"and":[26],"tool":[27,150],"budgets":[28],"on":[29,44,179],"redundant":[30,149],"steps":[31],"or":[32,42,148],"dead-end":[33],"trajectories.":[34],"Existing":[35],"budget-aware":[36],"methods":[37],"either":[38],"require":[39],"expensive":[40],"fine-tuning":[41],"rely":[43],"coarse,":[45],"trajectory-level":[46],"heuristics":[47],"that":[48,63,91,134,160,189,212],"cannot":[49],"intervene":[50],"mid-execution.":[51],"We":[52,152],"propose":[53],"the":[54,93,117,122,208],"Budget-Aware":[55],"Value":[56],"Tree":[57],"(BAVT),":[58],"training-free":[60],"inference-time":[61],"framework":[62],"models":[64],"multi-hop":[65,181],"reasoning":[66],"dynamic":[69],"search":[70],"tree":[71],"guided":[72],"by":[73],"step-level":[74],"value":[75,132],"estimation":[76],"within":[77],"single":[79],"backbone.":[81],"Another":[82],"key":[83],"innovation":[84],"is":[85],"budget-conditioned":[87],"node":[88,103],"selection":[89],"mechanism":[90],"uses":[92],"remaining":[94],"resource":[95,209],"ratio":[96],"natural":[99],"exponent":[101],"over":[102],"values,":[104],"providing":[105],"principled,":[107],"parameter-free":[108],"transition":[109],"from":[110],"broad":[111],"exploration":[112],"greedy":[114],"exploitation":[115],"budget":[118,175,214],"depletes.":[119],"To":[120],"combat":[121],"well-known":[123],"overconfidence":[124],"of":[125,146],"self-evaluation,":[127],"BAVT":[128,161,190,198],"employs":[129],"residual":[131],"predictor":[133],"scores":[135],"relative":[136],"progress":[137],"rather":[138],"than":[139],"absolute":[140],"state":[141],"quality,":[142],"enabling":[143],"reliable":[144],"pruning":[145],"uninformative":[147],"calls.":[151],"further":[153],"provide":[154],"theoretical":[156],"convergence":[157],"guarantee,":[158],"proving":[159],"reaches":[162],"terminal":[164],"answer":[165],"with":[166],"probability":[167],"at":[168,206],"least":[169],"$1-\u03b5$":[170],"under":[171,199],"explicit":[173],"finite":[174],"bound.":[176],"Extensive":[177],"evaluations":[178],"four":[180],"QA":[182],"benchmarks":[183],"across":[184],"two":[185],"model":[186],"families":[187],"demonstrate":[188],"consistently":[191],"outperforms":[192,217],"parallel":[193],"sampling":[194],"baselines.":[195],"Most":[196],"notably,":[197],"strict":[200],"low-budget":[201],"constraints":[202],"surpasses":[203],"baseline":[204],"performance":[205],"$4\\times$":[207],"allocation,":[210],"establishing":[211],"intelligent":[213],"management":[215],"fundamentally":[216],"brute-force":[218],"scaling.":[220]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-17T00:00:00"}