{"id":"https://openalex.org/W7203606795","doi":"https://doi.org/10.48550/arxiv.2608.14339","title":"Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents","display_name":"Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203606795","doi":"https://doi.org/10.48550/arxiv.2608.14339"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14339","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14339","pdf_url":"https://arxiv.org/pdf/2608.14339","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14339","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139775672","display_name":"Zhizhao Guan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guan, Zhizhao","raw_affiliation_strings":["Engineering Research Center of Machine Learning and Industry Intelligence","Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Machine Learning and Industry Intelligence","institution_ids":[]},{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133575993","display_name":"Chen Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huang, Chen","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924544","display_name":"Ziming Liu","orcid":"https://orcid.org/0009-0009-3355-6770","observed_orcids":["https://orcid.org/0009-0009-3355-6770"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Ziming","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101518132","display_name":"Hongru Liang","orcid":"https://orcid.org/0000-0002-4776-4505","observed_orcids":["https://orcid.org/0000-0002-4776-4505"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang, Hongru","raw_affiliation_strings":["Engineering Research Center of Machine Learning and Industry Intelligence","Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Machine Learning and Industry Intelligence","institution_ids":[]},{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136473535","display_name":"Wenqiang Lei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei, Wenqiang","raw_affiliation_strings":["Engineering Research Center of Machine Learning and Industry Intelligence","Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Machine Learning and Industry Intelligence","institution_ids":[]},{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090171111","display_name":"See-Kiong Ng","orcid":"https://orcid.org/0000-0001-6565-7511","observed_orcids":["https://orcid.org/0000-0001-6565-7511"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ng, See-Kiong","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807","observed_orcids":["https://orcid.org/0000-0001-6097-7807"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chua, Tat-Seng","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024409281","display_name":"Anthony G. Cohn","orcid":"https://orcid.org/0000-0002-7652-8907","observed_orcids":["https://orcid.org/0000-0002-7652-8907"]},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cohn, Anthony G","raw_affiliation_strings":["University of Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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":0.9932000041007996,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.003000000026077032,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8730000257492065},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6079999804496765},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6439999938011169},{"id":"https://openalex.org/keywords/decision-making","display_name":"decision-making","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.6741999983787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.600600004196167},{"id":"https://openalex.org/C134697681","wikidata":"https://www.wikidata.org/wiki/Q1609677","display_name":"Clearing","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C146778888","wikidata":"https://www.wikidata.org/wiki/Q836862","display_name":"Installation","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3587000072002411},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2662000060081482}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14339","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14339","pdf_url":"https://arxiv.org/pdf/2608.14339","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,"listed_in":[],"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.2608.14339","doi":"https://doi.org/10.48550/arxiv.2608.14339","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14339","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.14339","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14339","pdf_url":"https://arxiv.org/pdf/2608.14339","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203606795.pdf","grobid_xml":"https://content.openalex.org/works/W7203606795.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161558328","https://openalex.org/W7222997581","https://openalex.org/W7155030667","https://openalex.org/W7154174003","https://openalex.org/W7133354877","https://openalex.org/W4402671878","https://openalex.org/W7160945157","https://openalex.org/W7131869120","https://openalex.org/W4403578058","https://openalex.org/W7093372144"],"abstract_inverted_index":{"We":[0],"study":[1],"proactive":[2,46,104],"exploration":[3,86],"in":[4],"LLM":[5],"agents,":[6],"i.e.,":[7],"the":[8,64,93,101],"ability":[9],"to":[10,14,42,62,83],"explore":[11],"an":[12],"environment":[13],"acquire":[15],"information":[16],"that":[17,30],"improves":[18],"future":[19],"decision-making.":[20],"In":[21],"this":[22,32],"regard,":[23],"we":[24],"first":[25],"identify":[26],"two":[27,52],"fundamental":[28],"bottlenecks":[29],"hinder":[31],"capability":[33],"and":[34,44,70,97],"then":[35],"propose":[36],"\\ours,":[37],"a":[38],"novel":[39],"method":[40],"designed":[41],"instill":[43],"refine":[45],"exploration.":[47,105],"Specifically,":[48],"\\ours\\":[49,96],"consists":[50],"of":[51,67,95,103],"components:":[53],"(1)":[54],"Exploratory":[55],"Data":[56],"Construction,":[57],"which":[58,78],"synthesizes":[59],"exploration-rich":[60],"trajectories":[61],"mitigate":[63],"hindsight":[65],"bias":[66],"standard":[68],"demonstrations;":[69],"(2)":[71],"RL":[72],"Optimization":[73],"with":[74],"Contrastive":[75],"Signal":[76],"Guidance,":[77],"leverages":[79],"contrastive":[80],"trajectory":[81],"pairs":[82],"distinguish":[84],"productive":[85],"from":[87],"redundant":[88],"wandering.":[89],"Extensive":[90],"experiments":[91],"demonstrate":[92],"effectiveness":[94],"provide":[98],"insights":[99],"into":[100],"characteristics":[102],"Our":[106],"code":[107],"is":[108],"available":[109],"at:":[110],"https://github.com/GuanZhizhao/SAFARI.":[111]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-18T00:00:00"}