{"id":"https://openalex.org/W7128737136","doi":"https://doi.org/10.48448/vnds-7712","title":"Efficient Thought Space Exploration Through Strategic Intervention","display_name":"Efficient Thought Space Exploration Through Strategic Intervention","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128737136","doi":"https://doi.org/10.48448/vnds-7712"},"language":"en","primary_location":{"id":"doi:10.48448/vnds-7712","doi":"https://doi.org/10.48448/vnds-7712","is_oa":true,"landing_page_url":"https://doi.org/10.48448/vnds-7712","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/vnds-7712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125721756","display_name":"Hengyi Cai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Hengyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125727604","display_name":"Zhihong Deng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Zhihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102983694","display_name":"Ziheng Li","orcid":"https://orcid.org/0000-0002-3678-261X","observed_orcids":["https://orcid.org/0000-0002-3678-261X","https://orcid.org/0000-0001-5187-200X"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ziheng","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122478971","display_name":"Yuchen Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yuchen","raw_affiliation_strings":["Baidu Online Network Technology (Beijing) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Online Network Technology (Beijing) Co., Ltd","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050255638","display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947","observed_orcids":["https://orcid.org/0000-0002-9212-1947"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shuaiqiang","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125736334","display_name":"Xiaochi Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xiaochi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205","observed_orcids":["https://orcid.org/0000-0002-0684-6205","https://orcid.org/0000-0001-6813-680X"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin, Dawei","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]}],"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":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/T10028","display_name":"Topic Modeling","score":0.6532999873161316,"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/T10028","display_name":"Topic Modeling","score":0.6532999873161316,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2777999937534332,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.009200000204145908,"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/intervention-points","display_name":"intervention points","score":0.4860000014305115},{"id":"https://openalex.org/keywords/arithmetic-reasoning","display_name":"arithmetic reasoning","score":0.7950000166893005},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"commonsense reasoning","score":0.9589999914169312},{"id":"https://openalex.org/keywords/self-consistency","display_name":"self-consistency","score":0.6159999966621399},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.9710000157356262}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.795199990272522},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238999962806702},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36390000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3626999855041504},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/vnds-7712","doi":"https://doi.org/10.48448/vnds-7712","is_oa":true,"landing_page_url":"https://doi.org/10.48448/vnds-7712","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/vnds-7712","doi":"https://doi.org/10.48448/vnds-7712","is_oa":true,"landing_page_url":"https://doi.org/10.48448/vnds-7712","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6966934645","https://openalex.org/W7106785706","https://openalex.org/W4416172925","https://openalex.org/W7083842473","https://openalex.org/W7168028716","https://openalex.org/W4410355389","https://openalex.org/W7214726484","https://openalex.org/W4414969457","https://openalex.org/W7106835322","https://openalex.org/W4415332620"],"abstract_inverted_index":{"While":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"demonstrate":[5,148],"emerging":[6],"reasoning":[7,88,114,135,146,191],"capabilities,":[8],"current":[9],"inference-time":[10],"expansion":[11],"methods":[12,170],"incur":[13],"prohibitive":[14],"computational":[15],"costs":[16],"through":[17,61],"exhaustive":[18],"sampling.":[19],"Through":[20,125],"analyzing":[21],"decoding":[22,163],"trajectories,":[23],"we":[24,49],"observe":[25],"that":[26,57,70,85,103],"most":[27,173],"next-token":[28],"predictions":[29],"align":[30],"well":[31],"with":[32],"the":[33,110],"golden":[34],"output":[35],"except":[36],"a":[37,51,66,80,100,121],"few":[38],"critical":[39,75],"tokens":[40],"which":[41],"leads":[42],"to":[43,157,188],"deviation.":[44],"Inspired":[45],"by":[46,108,130,171],"this":[47,59],"phenomenon,":[48],"propose":[50],"novel":[52],"Hint-Practice":[53],"Reasoning":[54],"(HPR)":[55],"framework":[56],"operationalizes":[58],"insight":[60],"two":[62],"synergistic":[63],"components:":[64],"1)":[65],"hinter":[67],"(powerful":[68],"LLM)":[69],"provides":[71],"probabilistic":[72,123],"guidance":[73],"at":[74,172],"decision":[76],"points,":[77],"and":[78,116,144,159,167],"2)":[79],"practitioner":[81],"(efficient":[82],"smaller":[83],"model)":[84],"executes":[86],"major":[87],"steps.":[89],"The":[90],"framework's":[91],"core":[92],"innovation":[93],"lies":[94],"in":[95,120],"Distributional":[96],"Inconsistency":[97],"Reduction":[98],"(DIR),":[99],"theoretically-grounded":[101],"metric":[102],"dynamically":[104],"identifies":[105],"intervention":[106],"points":[107],"quantifying":[109],"divergence":[111],"between":[112],"practitioner's":[113],"trajectory":[115],"hinter's":[117],"expected":[118],"distribution":[119],"tree-structured":[122],"space.":[124],"iterative":[126],"tree":[127],"updates":[128],"guided":[129],"DIR,":[131],"HPR":[132],"reweights":[133],"promising":[134],"paths":[136],"while":[137,162,177],"deprioritizing":[138],"low-probability":[139],"branches.":[140],"Experiments":[141],"across":[142],"arithmetic":[143],"commonsense":[145],"benchmarks":[147],"HPR's":[149],"state-of-the-art":[150],"efficiency-accuracy":[151],"tradeoffs:":[152],"it":[153],"achieves":[154],"comparable":[155],"performance":[156],"self-consistency":[158],"MCTS":[160],"baselines":[161],"only":[164],"1/5":[165],"tokens,":[166],"outperforms":[168],"existing":[169],"5.1%":[174],"absolute":[175],"accuracy":[176],"maintaining":[178],"similar":[179],"or":[180],"lower":[181],"FLOPs.":[182],"Our":[183],"code":[184],"will":[185],"be":[186],"open-sourced":[187],"catalyze":[189],"efficient":[190],"research.":[192]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-02-13T00:00:00"}