{"id":"https://openalex.org/W7155087373","doi":"https://doi.org/10.48550/arxiv.2604.18131","title":"Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration","display_name":"Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155087373","doi":"https://doi.org/10.48550/arxiv.2604.18131"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.18131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100708486","display_name":"Qifan Zhang","orcid":"https://orcid.org/0000-0002-1521-7881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134146003","display_name":"Dongyang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Dongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046409172","display_name":"Tianqing Fang","orcid":"https://orcid.org/0000-0002-0186-8253"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Tianqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134128117","display_name":"Jia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134197983","display_name":"Jing Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134115119","display_name":"Nuo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Nuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134141893","display_name":"Haitao Mi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mi, Haitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134111168","display_name":"Yan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yan","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.536300003528595,"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":0.536300003528595,"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/T12090","display_name":"Language and cultural evolution","score":0.08590000122785568,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.05530000105500221,"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/task","display_name":"Task (project management)","score":0.6796000003814697},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6358000040054321},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6031000018119812},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5080000162124634},{"id":"https://openalex.org/keywords/paradigm-shift","display_name":"Paradigm shift","score":0.3345000147819519}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6796000003814697},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5856000185012817},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48989999294281006},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27230000495910645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.18131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Most":[0,141],"agents":[1,32],"today":[2],"``self-evolve''":[3],"by":[4,10],"following":[5],"rewards":[6,103],"and":[7,92,125,139],"rules":[8],"defined":[9],"humans.":[11],"However,":[12],"this":[13,28,51,127],"process":[14],"remains":[15],"fundamentally":[16],"dependent":[17],"on":[18,72,137],"external":[19,102],"supervision;":[20],"without":[21],"human":[22,105],"guidance,":[23],"the":[24,82,87,98,143,156],"evolution":[25,131],"stops.":[26],"In":[27],"work,":[29],"we":[30,53],"train":[31],"to":[33,39,46,85,90,112,114,123,129,154],"possess":[34],"an":[35,55,63],"intrinsic":[36],"meta-evolution":[37],"capability":[38],"spontaneously":[40,108],"learn":[41],"about":[42],"unseen":[43],"environments":[44,116],"prior":[45],"task":[47],"execution.":[48],"To":[49],"instill":[50],"ability,":[52],"design":[54],"outcome-based":[56],"reward":[57,76],"mechanism":[58],"that":[59],"measures":[60],"how":[61,89],"much":[62],"agent's":[64],"self-generated":[65],"world":[66,145],"knowledge":[67,146],"improves":[68],"its":[69,118],"success":[70],"rate":[71],"downstream":[73],"tasks.":[74],"This":[75],"signal":[77],"is":[78],"used":[79],"exclusively":[80],"during":[81],"training":[83],"phase":[84],"teach":[86],"model":[88,153],"explore":[91],"summarize":[93],"effectively.":[94],"At":[95],"inference":[96],"time,":[97],"agent":[99],"requires":[100],"no":[101],"or":[104],"instructions.":[106],"It":[107],"performs":[109],"native":[110,130],"self-evolution":[111],"adapt":[113],"unknown":[115],"using":[117],"internal":[119],"parameters.":[120],"When":[121],"applied":[122],"Qwen3-30B":[124],"Seed-OSS-36B,":[126],"shift":[128],"yields":[132],"a":[133,149,160],"20%":[134],"performance":[135],"increase":[136],"WebVoyager":[138],"WebWalker.":[140],"strikingly,":[142],"generated":[144],"even":[147],"enables":[148],"compact":[150],"14B":[151],"Qwen3":[152],"outperform":[155],"unassisted":[157],"Gemini-2.5-Flash,":[158],"establishing":[159],"new":[161],"paradigm":[162],"for":[163],"truly":[164],"evolving":[165],"agents.":[166]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}