{"id":"https://openalex.org/W7164833996","doi":"https://doi.org/10.1145/3805622.3810701","title":"Evo-CuRL: Curriculum-Aware Reinforcement Learning over Code Lineage Graphs for Software Engineering Reasoning","display_name":"Evo-CuRL: Curriculum-Aware Reinforcement Learning over Code Lineage Graphs for Software Engineering Reasoning","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164833996","doi":"https://doi.org/10.1145/3805622.3810701"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810701","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810701","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810701","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129730136","display_name":"Wei Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Tan","raw_affiliation_strings":["University of Bristol, Bristol, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-6417-299X","affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol, United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631364","display_name":"Yuanhao Li","orcid":"https://orcid.org/0000-0002-9012-4503"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanhao Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1275-4298","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138656747","display_name":"Wenkai Liang","orcid":"https://orcid.org/0009-0002-0250-9073"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenkai Liang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0250-9073","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9645025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1327","last_page":"1335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.8959000110626221,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.8959000110626221,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.014499999582767487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7386000156402588},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5370000004768372},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4903999865055084},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.45739999413490295},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41350001096725464},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.4074000120162964},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.39890000224113464},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38960000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765999972820282},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7386000156402588},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023000240325928},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46470001339912415},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.45739999413490295},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C174683762","wikidata":"https://www.wikidata.org/wiki/Q609588","display_name":"Component-based software engineering","level":4,"score":0.3296999931335449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.29499998688697815},{"id":"https://openalex.org/C76518257","wikidata":"https://www.wikidata.org/wiki/Q271680","display_name":"Software framework","level":5,"score":0.2939999997615814},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.28029999136924744},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.26600000262260437},{"id":"https://openalex.org/C102379954","wikidata":"https://www.wikidata.org/wiki/Q2589940","display_name":"Call graph","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810701","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810701","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810701","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810701","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7657176852226257,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4402442868"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0,81],"learning":[1],"(RL)":[2],"with":[3,18,237],"rule-based":[4],"rewards":[5],"has":[6],"recently":[7],"shown":[8],"remarkable":[9],"potential":[10],"for":[11],"improving":[12],"large":[13],"language":[14,247],"model":[15,162,232],"(LLM)":[16],"reasoning,":[17,244],"approaches":[19],"like":[20,229],"SWE-RL":[21],"demonstrating":[22],"that":[23,85,104,116,142,208,251],"software":[24,101,255],"evolution":[25,102],"data":[26,103,256],"can":[27],"serve":[28],"as":[29,40],"an":[30],"effective":[31],"training":[32,140,145],"signal.":[33],"However,":[34],"existing":[35],"methods":[36],"treat":[37],"pull":[38],"requests":[39],"independent,":[41],"identically":[42],"distributed":[43],"samples":[44,144],"and":[45,62,108,131,189,213,245],"rely":[46],"on":[47,173,186,191,241,254],"flat":[48],"sequence-similarity":[49],"rewards,":[50],"ignoring":[51],"the":[52,58,63,161,210,214],"rich":[53],"structural":[54,128],"information":[55],"embedded":[56],"in":[57],"codebase\u2019s":[59],"dependency":[60,133],"graph":[61,99],"natural":[64],"difficulty":[65],"gradient":[66],"across":[67],"different":[68],"types":[69],"of":[70,123,175],"code":[71,97],"changes.":[72,171],"In":[73],"this":[74],"paper,":[75],"we":[76,94,136],"introduce":[77,137],"Evo-CuRL":[78],"(Evolutionary":[79],"Curriculum":[80],"Learning),":[82],"a":[83,96,112,138,156,182],"framework":[84],"addresses":[86],"both":[87,209],"limitations":[88],"through":[89],"two":[90],"synergistic":[91],"innovations.":[92],"First,":[93],"construct":[95],"lineage":[98],"from":[100,147],"captures":[105],"inter-file":[106],"dependencies":[107],"modification":[109],"histories,":[110],"enabling":[111],"graph-aware":[113,211],"hierarchical":[114],"reward":[115,212],"evaluates":[117],"generated":[118],"patches":[119],"at":[120],"three":[121],"levels":[122],"granularity:":[124],"local":[125],"sequence":[126],"similarity,":[127],"AST":[129],"consistency,":[130],"global":[132],"coherence.":[134],"Second,":[135],"curriculum-aware":[139],"scheduler":[141,216],"adaptively":[143],"instances":[146],"easy":[148],"(single-file":[149],"edits)":[150],"to":[151],"hard":[152],"(cross-module":[153],"refactors)":[154],"using":[155],"multi-armed":[157],"bandit":[158],"formulation,":[159],"ensuring":[160],"builds":[163],"foundational":[164],"patch-generation":[165],"skills":[166],"before":[167],"tackling":[168],"complex":[169],"multi-file":[170],"Trained":[172],"top":[174],"Llama-3,":[176],"our":[177,231],"resulting":[178],"model,":[179],"Llama3-Evo-CuRL-70B,":[180],"achieves":[181],"45.6%":[183],"resolve":[184],"rate":[185],"SWE-bench":[187,192],"Verified":[188],"38.7%":[190],"Lite,":[193],"establishing":[194],"new":[195],"state-of-the-art":[196],"results":[197],"among":[198],"open-source":[199],"models":[200],"under":[201],"100B":[202],"parameters.":[203],"Comprehensive":[204],"ablation":[205],"studies":[206],"confirm":[207],"curriculum":[215],"contribute":[217],"meaningfully:":[218],"removing":[219],"either":[220],"component":[221],"degrades":[222],"performance":[223],"by":[224],"2.5\u20133.8":[225],"percentage":[226],"points.":[227],"Furthermore,":[228],"SWE-RL,":[230],"exhibits":[233],"emergent":[234],"out-of-domain":[235],"generalization,":[236],"even":[238],"larger":[239],"improvements":[240],"coding,":[242],"mathematical":[243],"general":[246],"understanding":[248],"benchmarks,":[249],"suggesting":[250],"structured":[252],"RL":[253],"cultivates":[257],"broadly":[258],"transferable":[259],"reasoning":[260],"capabilities.":[261]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}