{"id":"https://openalex.org/W7154955564","doi":"https://doi.org/10.48550/arxiv.2604.15830","title":"Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning","display_name":"Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154955564","doi":"https://doi.org/10.48550/arxiv.2604.15830"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15830","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.2604.15830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126450348","display_name":"Yangyi Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Yangyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134083718","display_name":"Jiaye Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Jiaye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126519510","display_name":"Xiaoliang Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Xiaoliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134074566","display_name":"Cong Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Cong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126721375","display_name":"Haolin Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Haolin","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/T10028","display_name":"Topic Modeling","score":0.565500020980835,"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/T10028","display_name":"Topic Modeling","score":0.565500020980835,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17630000412464142,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06809999793767929,"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/overfitting","display_name":"Overfitting","score":0.8136000037193298},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.699999988079071},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.382099986076355},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.2903999984264374},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.27730000019073486},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.26820001006126404}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8136000037193298},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.699999988079071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4526999890804291},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15830","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.2604.15830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15830","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,116],"has":[2],"become":[3],"a":[4,15,76],"powerful":[5],"approach":[6],"for":[7],"enhancing":[8],"large":[9],"language":[10],"model":[11,130],"reasoning,":[12],"but":[13],"faces":[14],"fundamental":[16],"dilemma:":[17],"training":[18,29],"on":[19,30,102,121],"easy":[20],"problems":[21,32],"can":[22,66],"cause":[23],"overfitting":[24],"and":[25,63,83,105],"pass@k":[26,71,140],"degradation,":[27],"while":[28,58,138],"hard":[31],"often":[33],"results":[34],"in":[35],"sparse":[36],"rewards.":[37],"Recent":[38],"question":[39],"augmentation":[40],"methods":[41],"address":[42],"this":[43],"by":[44],"prepending":[45],"partial":[46],"solutions":[47],"as":[48],"hints.":[49],"However,":[50],"uniform":[51],"hint":[52,77],"provision":[53],"may":[54],"introduce":[55],"redundant":[56],"information":[57],"missing":[59],"critical":[60,85],"reasoning":[61,68,86,96,124],"bottlenecks,":[62],"excessive":[64],"hints":[65,100],"reduce":[67],"diversity,":[69],"causing":[70],"degradation.":[72],"We":[73],"propose":[74],"\\textbf{PieceHint},":[75],"injection":[78],"framework":[79],"that":[80,127],"strategically":[81],"identifies":[82],"provides":[84],"steps":[87],"during":[88],"training.":[89],"By":[90],"scoring":[91],"the":[92],"importance":[93],"of":[94],"different":[95],"steps,":[97],"selectively":[98],"allocating":[99],"based":[101],"problem":[103],"difficulty,":[104],"progressively":[106],"withdrawing":[107],"scaffolding,":[108],"PieceHint":[109],"enables":[110],"models":[111],"to":[112,117,135],"transition":[113],"from":[114],"guided":[115],"independent":[118],"reasoning.":[119],"Experiments":[120],"six":[122],"mathematical":[123],"benchmarks":[125],"show":[126],"our":[128],"1.5B":[129],"achieves":[131],"comparable":[132],"average":[133],"performance":[134],"32B":[136],"baselines":[137],"preserving":[139],"diversity":[141],"across":[142],"all":[143],"$k$":[144],"values.":[145]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-21T00:00:00"}