{"id":"https://openalex.org/W7204210112","doi":"https://doi.org/10.48550/arxiv.2608.21871","title":"The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning","display_name":"The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204210112","doi":"https://doi.org/10.48550/arxiv.2608.21871"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21871","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21871","pdf_url":"https://arxiv.org/pdf/2608.21871","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050012159","display_name":"Jing Yu","orcid":"https://orcid.org/0000-0001-6205-1880","observed_orcids":["https://orcid.org/0000-0001-6205-1880"]},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Jing","raw_affiliation_strings":["College of Computer and Information Engineering , Xi'an University of Architecture and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering , Xi'an University of Architecture and Technology","institution_ids":["https://openalex.org/I148099405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072469364","display_name":"Shengchao Chen","orcid":"https://orcid.org/0000-0001-9992-2264","observed_orcids":["https://orcid.org/0000-0001-9992-2264","https://orcid.org/0009-0001-0078-9764"]},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chen, Shengchao","raw_affiliation_strings":["Australian Artificial Intelligence Institute , University of Technology Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute , University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148165284","display_name":"Yiyun Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Yiyun","raw_affiliation_strings":["College of Computer and Information Engineering , Xi'an University of Architecture and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering , Xi'an University of Architecture and Technology","institution_ids":["https://openalex.org/I148099405"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.3862000107765198,"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":0.3862000107765198,"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/T10028","display_name":"Topic Modeling","score":0.23659999668598175,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12729999423027039,"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/large-language-model-reasoning","display_name":"large language model reasoning","score":0.906000018119812},{"id":"https://openalex.org/keywords/pursuit-evasion-games","display_name":"pursuit-evasion games","score":0.8740000128746033},{"id":"https://openalex.org/keywords/verifiable-rewards","display_name":"verifiable rewards","score":0.5879999995231628},{"id":"https://openalex.org/keywords/lures","display_name":"lures","score":0.5809999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318999767303467},{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.7297000288963318},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.677299976348877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.582099974155426},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C3019612716","wikidata":"https://www.wikidata.org/wiki/Q730920","display_name":"Problem solver","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2776796639","wikidata":"https://www.wikidata.org/wiki/Q18206654","display_name":"Drooling","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21871","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21871","pdf_url":"https://arxiv.org/pdf/2608.21871","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.2608.21871","doi":"https://doi.org/10.48550/arxiv.2608.21871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21871","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:2608.21871","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21871","pdf_url":"https://arxiv.org/pdf/2608.21871","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204210112.pdf","grobid_xml":"https://content.openalex.org/works/W7204210112.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2616430965","https://openalex.org/W2736601468","https://openalex.org/W2963577640","https://openalex.org/W3134642945","https://openalex.org/W4388718089","https://openalex.org/W4391631327","https://openalex.org/W4400141990","https://openalex.org/W4401306886","https://openalex.org/W4401306979","https://openalex.org/W4403883066","https://openalex.org/W4404987838","https://openalex.org/W4405655184","https://openalex.org/W4414281281","https://openalex.org/W4416261883","https://openalex.org/W4416373167","https://openalex.org/W6929629322","https://openalex.org/W7160095038"],"related_works":["https://openalex.org/W7222249566","https://openalex.org/W7138081061","https://openalex.org/W4415035719","https://openalex.org/W4415914641","https://openalex.org/W7160951781","https://openalex.org/W6929629322","https://openalex.org/W4416010183","https://openalex.org/W7161030211","https://openalex.org/W4416065883","https://openalex.org/W7214630903"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,42],"with":[2,57,148],"verifiable":[3,96,163],"rewards":[4,60],"has":[5],"become":[6],"the":[7,55,109,149,158,178],"dominant":[8],"recipe":[9],"for":[10],"improving":[11],"large":[12,19],"language":[13],"model":[14,180],"reasoning,":[15],"yet":[16],"it":[17,93,112],"presumes":[18],"human-curated":[20],"task":[21,197],"collections.":[22],"Zero-data":[23],"self-play":[24,65],"removes":[25],"this":[26],"dependency,":[27],"but":[28],"existing":[29],"methods":[30],"vet":[31],"learnability":[32],"only":[33],"by":[34],"probing":[35],"candidates":[36],"and":[37,53,166],"rejecting":[38],"post":[39],"hoc,":[40],"never":[41],"where":[43],"along":[44,77],"an":[45,72],"environment's":[46,79],"difficulty":[47,80],"axis":[48,81],"to":[49,82],"place":[50],"a":[51,67,88,103,123,129,153],"task,":[52],"credit":[54],"solver":[56,110],"sparse":[58],"terminal":[59,150],"alone.":[61],"We":[62],"recast":[63],"zero-data":[64],"as":[66],"pursuit-evasion":[68],"game:":[69],"in":[70,140],"LURE,":[71],"LLM":[73],"evader":[74,99],"positions":[75],"tasks":[76],"each":[78],"stay":[83],"one":[84],"step":[85],"ahead":[86],"of":[87,116],"planner-executor":[89],"pursuer":[90,134],"that":[91,106,156],"hunts":[92],"down":[94],"through":[95],"interaction.":[97],"The":[98,133],"is":[100,145],"trained":[101,189],"on":[102,113],"capture-frontier":[104],"reward":[105],"peaks":[107],"when":[108],"captures":[111],"exactly":[114],"half":[115],"its":[117],"rollouts,":[118],"turning":[119],"barely":[120],"catchable":[121],"into":[122],"learned":[124],"positioning":[125],"strategy":[126],"rather":[127],"than":[128,187],"hand-tuned":[130],"rejection":[131],"band.":[132],"earns":[135],"capture-anchored":[136],"dense":[137],"process":[138],"credit,":[139],"which":[141],"monotone":[142],"verifier":[143],"progress":[144],"group-normalized":[146],"jointly":[147],"capture":[151],"under":[152,174],"round-anchored":[154],"KL":[155],"keeps":[157],"co-evolution":[159],"stable.":[160],"Across":[161],"three":[162,167,196],"reasoning":[164],"environments":[165],"backbone":[168],"families,":[169],"LURE":[170],"outperforms":[171],"advanced":[172],"baselines":[173,190],"unified/specialist":[175],"settings,":[176],"while":[177],"unified":[179],"attains":[181],"stronger":[182],"aggregate":[183],"OOD":[184],"zero-shot":[185],"accuracy":[186],"all":[188],"across":[191],"nine":[192],"held-out":[193],"benchmarks":[194],"from":[195],"families.":[198]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}