{"id":"https://openalex.org/W4416450646","doi":"https://doi.org/10.18653/v1/2026.acl-long.100","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","display_name":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416450646","doi":"https://doi.org/10.18653/v1/2026.acl-long.100"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.100","pdf_url":"https://aclanthology.org/2026.acl-long.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.100.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100320731","display_name":"Jiawei Liu","orcid":"https://orcid.org/0000-0001-5163-110X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013179975","display_name":"Qisi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qisi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101760682","display_name":"Jianshu Zhang","orcid":"https://orcid.org/0000-0002-2713-2535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianshu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414580","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0003-0866-8008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085254654","display_name":"Defu Lian","orcid":"https://orcid.org/0000-0002-3507-9607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Defu Lian","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02351624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2211","last_page":"2226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.34389999508857727,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.34389999508857727,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.21410000324249268,"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":0.06809999793767929,"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/security-token","display_name":"Security token","score":0.7049000263214111},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5418000221252441},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5031999945640564},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3779999911785126},{"id":"https://openalex.org/keywords/semantic-equivalence","display_name":"Semantic equivalence","score":0.37130001187324524},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3066999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541000247001648},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7049000263214111},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406000018119812},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48570001125335693},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C37926939","wikidata":"https://www.wikidata.org/wiki/Q7449061","display_name":"Semantic equivalence","level":4,"score":0.37130001187324524},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.100","pdf_url":"https://aclanthology.org/2026.acl-long.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.16312","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.16312","pdf_url":"https://arxiv.org/pdf/2505.16312","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.16312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.16312","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:10.18653/v1/2026.acl-long.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.100","pdf_url":"https://aclanthology.org/2026.acl-long.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416450646.pdf","grobid_xml":"https://content.openalex.org/works/W4416450646.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"excel":[4],"at":[5],"complex":[6],"reasoning":[7,62,104],"through":[8],"search":[9],"algorithms,":[10],"yet":[11,50],"current":[12],"strategies":[13],"often":[14,102],"suffer":[15],"from":[16],"massive":[17],"token":[18,96,115],"consumption":[19,116],"due":[20],"to":[21,32,109],"redundant":[22],"exploration":[23],"of":[24,80],"semantically":[25,57],"equivalent":[26,58],"steps.Existing":[27],"semantic":[28],"similarity":[29],"methods":[30],"struggle":[31],"accurately":[33],"identify":[34],"such":[35],"equivalence":[36,83],"in":[37],"domainspecific":[38],"contexts":[39],"like":[40],"mathematical":[41,73],"reasoning.To":[42],"address":[43],"this,":[44],"we":[45,70],"propose":[46],"EquivPruner,":[47],"a":[48,81],"simple":[49],"effective":[51],"approach":[52],"that":[53,92],"identifies":[54],"and":[55,89,101],"prunes":[56],"actions":[59],"during":[60],"LLM":[61],"search.We":[63],"also":[64,120],"introduce":[65],"MathEquiv,":[66],"the":[67,78],"first":[68],"dataset":[69],"created":[71],"for":[72],"statement":[74],"equivalence,":[75],"which":[76],"enables":[77],"training":[79],"lightweight":[82],"detector.Extensive":[84],"experiments":[85],"across":[86],"various":[87],"models":[88],"tasks":[90],"demonstrate":[91],"EquivPruner":[93,113],"significantly":[94],"reduces":[95],"consumption,":[97],"improving":[98,121],"searching":[99],"efficiency":[100],"bolstering":[103],"accuracy.For":[105],"instance,":[106],"when":[107],"applied":[108],"Qwen2.5-Math-7B-Instruct":[110],"on":[111],"GSM8K,":[112],"reduced":[114],"by":[117],"48.1%":[118],"while":[119],"accuracy.":[122]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}