{"id":"https://openalex.org/W7166863300","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1434","title":"VANE: Guiding High-Value Exploration in RLVR via Outcome-Process Novelty Shaping","display_name":"VANE: Guiding High-Value Exploration in RLVR via Outcome-Process Novelty Shaping","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166863300","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1434"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1434","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1434","pdf_url":"https://aclanthology.org/2026.findings-acl.1434.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.1434.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139816130","display_name":"Xu He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139804394","display_name":"Jialiang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialiang Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006269349","display_name":"Fucheng Xiong","orcid":"https://orcid.org/0000-0002-2326-3263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fucheng Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025780527","display_name":"Haodong Zhao","orcid":"https://orcid.org/0000-0002-4405-1649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haodong Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139776349","display_name":"Xingyang li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyang li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839379","display_name":"Ke Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[]}],"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":0.8248307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28721","last_page":"28739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10933","display_name":"Real-Time Systems Scheduling","score":0.06069999933242798,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.06069999933242798,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.02930000051856041,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.023000000044703484,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/novelty","display_name":"Novelty","score":0.4546000063419342},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.27720001339912415},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.27300000190734863},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25920000672340393},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2587999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583999752998352},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453000009059906},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23980000615119934},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23549999296665192}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1434","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1434","pdf_url":"https://aclanthology.org/2026.findings-acl.1434.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.1434","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1434","pdf_url":"https://aclanthology.org/2026.findings-acl.1434.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166863300.pdf","grobid_xml":"https://content.openalex.org/works/W7166863300.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"with":[2],"Verifiable":[3],"Rewards":[4],"(RLVR)":[5],"frequently":[6],"suffers":[7],"from":[8],"mode":[9],"collapse":[10],"due":[11],"to":[12,37],"the":[13,60,69,112,117],"inherent":[14],"sparsity":[15],"of":[16,116],"feedback":[17],"signals.While":[18],"strategies":[19],"such":[20,99],"as":[21,100],"entropy":[22],"regularization":[23],"introduce":[24],"randomness,":[25],"they":[26],"lack":[27],"directionality.Simply":[28],"incorporating":[29],"diversity":[30],"rewards":[31],"is":[32],"overly":[33],"one-sided":[34],"and":[35,68,108,114],"fails":[36],"identify":[38],"potential":[39],"logical":[40],"errors":[41],"or":[42,65],"hallucinations.To":[43],"address":[44],"these":[45],"limitations,":[46],"we":[47],"propose":[48],"VANE":[49,77],"(Value-Aligned":[50],"Novelty":[51],"Exploration),":[52],"a":[53,79],"method":[54],"that":[55,82],"simultaneously":[56],"quantifies":[57],"novelty":[58],"across":[59],"outcome":[61],"space":[62,72],"(via":[63,73],"reward":[64],"solution":[66],"divergence)":[67],"semantic":[70,74],"process":[71,75],"divergence).Moreover,":[76],"employs":[78],"value-alignment":[80],"mechanism":[81],"symmetrically":[83],"amplifies":[84],"scarce,":[85],"high-quality":[86],"solutions":[87],"while":[88],"explicitly":[89],"penalizing":[90],"diverse":[91],"yet":[92],"erroneous":[93],"reasoning":[94,107],"paths.Extensive":[95],"experiments":[96],"on":[97],"models":[98],"Qwen2.5-Math-7Bacross":[101],"eight":[102],"benchmarks-encompassing":[103],"both":[104],"large-scale":[105],"mathematical":[106],"out-ofdistribution":[109],"(OOD)":[110],"tasks-demonstrate":[111],"effectiveness":[113],"generalization":[115],"proposed":[118],"method.":[119]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}