{"id":"https://openalex.org/W7166874779","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1814","title":"BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search","display_name":"BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166874779","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1814"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1814","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1814","pdf_url":"https://aclanthology.org/2026.findings-acl.1814.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1814.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139752678","display_name":"Shiyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102965197","display_name":"Yongjing Yin","orcid":"https://orcid.org/0000-0003-1138-4612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongjing Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760961","display_name":"Jianhao Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianhao Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139729608","display_name":"Yunbo Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunbo Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719835","display_name":"Qinggang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinggang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139752436","display_name":"Bei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735912","display_name":"Xin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139790519","display_name":"Jingang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139817245","display_name":"Xunliang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunliang Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139774715","display_name":"Jinsong Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinsong Su","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":0.86320353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36408","last_page":"36426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5266000032424927,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5266000032424927,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.09149999916553497,"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/T12288","display_name":"Optimization and Search Problems","score":0.0877000018954277,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.3310999870300293},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3018999993801117},{"id":"https://openalex.org/keywords/agency","display_name":"Agency (philosophy)","score":0.2773999869823456},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2676999866962433},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25450000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536899983882904},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3118000030517578},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1814","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1814","pdf_url":"https://aclanthology.org/2026.findings-acl.1814.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1814","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1814","pdf_url":"https://aclanthology.org/2026.findings-acl.1814.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4823719263076782,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G4177599645","display_name":"\u7caa\u83cc\u79fb\u690d\u5bf9\u809d\u786c\u5316\u5927\u9f20\u7ebf\u7c92\u4f53\u5fae\u81ea\u566c\u3001\u6c27\u5316\u5e94\u6fc0\u3001\u7cd6\u8102\u4ee3\u8c22\u53ca\u809d\u7ec6\u80de\u51cb\u4ea1\u5f71\u54cd\u7684\u673a\u5236\u7814\u7a76","funder_award_id":"2024J011001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"}],"funders":[{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166874779.pdf","grobid_xml":"https://content.openalex.org/works/W7166874779.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"RL-based":[0],"agentic":[1,155],"search":[2,156],"enables":[3],"LLMs":[4],"to":[5,38,65,90],"solve":[6],"complex":[7],"questions":[8],"via":[9,24],"dynamic":[10],"planning":[11],"and":[12,43,119],"external":[13],"search.While":[14],"this":[15,77,128],"approach":[16],"significantly":[17],"enhances":[18,150],"accuracy":[19],"with":[20],"agent":[21],"policies":[22],"optimized":[23],"large-scale":[25],"reinforcement":[26],"learning,":[27],"we":[28,79],"identify":[29],"a":[30,85,103,140],"critical":[31],"gap":[32],"in":[33,73],"reliability:":[34],"these":[35],"agents":[36],"fail":[37],"recognize":[39],"their":[40],"reasoning":[41,56,115],"boundaries":[42],"rarely":[44],"admit":[45],"\"I":[46],"DON'T":[47],"KNOW\"":[48],"(IDK)":[49],"even":[50],"when":[51,113],"evidence":[52],"is":[53],"insufficient":[54],"or":[55],"reaches":[57,116],"its":[58,117],"limit.The":[59],"lack":[60],"of":[61,154],"reliability":[62,153],"often":[63],"leads":[64],"plausible":[66],"but":[67],"unreliable":[68],"answers,":[69],"introducing":[70],"significant":[71],"risks":[72],"many":[74],"real-world":[75],"scenarios.To":[76],"end,":[78],"propose":[80],"Boundary-Aware":[81],"Policy":[82],"Optimization":[83],"(BAPO),":[84],"novel":[86],"RL":[87],"framework":[88],"designed":[89],"cultivate":[91],"reliable":[92],"boundary":[93],"awareness":[94],"without":[95],"compromising":[96],"accuracy.BAPO":[97],"introduces":[98],"two":[99],"key":[100],"components:":[101],"(i)":[102],"group-based":[104],"boundary-aware":[105],"reward":[106,123,129],"that":[107,125,147],"encourages":[108],"an":[109,121],"IDK":[110,138],"response":[111],"only":[112],"the":[114,134,151],"limit,":[118],"(ii)":[120],"adaptive":[122],"modulator":[124],"strategically":[126],"suspends":[127],"during":[130],"early":[131],"exploration,":[132],"preventing":[133],"model":[135],"from":[136],"exploiting":[137],"as":[139],"shortcut.Extensive":[141],"experiments":[142],"on":[143],"four":[144],"benchmarks":[145],"demonstrate":[146],"BAPO":[148],"substantially":[149],"overall":[152],"1":[157],".":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}