{"id":"https://openalex.org/W7160306164","doi":"https://doi.org/10.48550/arxiv.2605.00942","title":"PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation","display_name":"PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160306164","doi":"https://doi.org/10.48550/arxiv.2605.00942"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00942","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":null,"license_id":null,"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.2605.00942","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135378156","display_name":"Gourisetty Venkata Sai Koushik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koushik, Gourisetty Venkata Sai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135375902","display_name":"Dama Aditya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya, Dama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135284696","display_name":"Mahankali Harish Sai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sai, Mahankali Harish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135340992","display_name":"Peddi Siddarhta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddarhta, Peddi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135391569","display_name":"Shadab Ahmad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad, Shadab","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128778295","display_name":"Vivek Yelleti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yelleti, Vivek","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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9315000176429749,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9315000176429749,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.016599999740719795,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.014800000004470348,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6743999719619751},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6255000233650208},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/code-coverage","display_name":"Code coverage","score":0.4343000054359436},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4293000102043152},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.4049000144004822}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513000130653381},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6255000233650208},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4878000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4659000039100647},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00942","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.00942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00942","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":null,"license_id":null,"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":{"Developing":[0],"effective":[1],"test":[2,36,60],"cases":[3,37],"capable":[4],"of":[5,65,89,106,160,200,224],"thoroughly":[6],"exercising":[7],"large-scale":[8],"software":[9],"systems":[10,17],"is":[11,49,100,186,226,237],"inherently":[12],"difficult,":[13],"especially":[14],"if":[15],"such":[16,114],"have":[18],"voluminous,":[19],"complex,":[20],"and":[21,76,135,164,171,196,202],"deeply":[22],"nested":[23],"source":[24,79,91,131,175],"codes.":[25],"In":[26,68,93],"this":[27],"work,":[28],"we":[29],"present":[30],"a":[31,39,96,158],"novel":[32],"approach":[33,63],"for":[34,168,173,209],"generating":[35],"using":[38,228,240],"reinforcement":[40],"learning-driven":[41],"agentic":[42],"framework":[43],"where":[44],"Proximal":[45],"Policy":[46],"Optimization":[47],"(PPO)":[48],"coupled":[50],"with":[51],"an":[52],"LLM":[53,142],"engine":[54,143],"to":[55,102,139,217],"guide":[56],"prompt":[57,246],"selection":[58,247],"during":[59],"generation.":[61],"Our":[62],"consists":[64],"two":[66],"phases.":[67],"Phase":[69,94],"I,":[70],"the":[71,78,86,90,104,124,130,141,149,189,222,231],"ToT-guided":[72],"optimization":[73],"agent":[74,153],"partitions":[75],"minimizes":[77],"code":[80,132,176],"by":[81,249],"removing":[82],"redundancies":[83],"without":[84],"changing":[85],"functional":[87],"behavior":[88],"code.":[92],"II,":[95],"PPO-based":[97],"policy":[98],"network":[99],"trained":[101],"solve":[103],"problem":[105],"selecting":[107],"prompts":[108],"among":[109],"eight":[110],"different":[111],"prompting":[112,254],"techniques,":[113],"as":[115],"Boundary":[116],"Value":[117],"Analysis,":[118],"Random":[119],"Fuzzing,":[120],"etc.,":[121],"based":[122,156],"on":[123,157,181,230,256],"inputted":[125],"11-dimensional":[126],"state":[127],"vector":[128],"representing":[129],"complexity":[133],"metrics":[134,138],"live":[136],"coverage":[137,204,223],"direct":[140],"towards":[144],"exploring":[145],"unvisited":[146],"paths":[147],"in":[148,162,198,205,234],"program.":[150],"The":[151],"PPO":[152,250],"receives":[154],"rewards":[155,172],"combination":[159],"increases":[161],"line":[163,203],"branch":[165,201],"coverages,":[166],"penalties":[167],"unexplored":[169],"branches,":[170],"reducing":[174],"length.":[177],"From":[178],"experiments":[179],"conducted":[180],"twenty":[182],"benchmark":[183],"programs,":[184],"it":[185,236],"evident":[187],"that":[188,244],"proposed":[190],"approach,":[191],"PPO-LLM,":[192],"outperforms":[193,252],"CBMC,":[194],"kS-LLM,":[195],"kS-LLM++":[197],"terms":[199],"almost":[206],"all":[207],"cases,":[208],"various":[210],"loop":[211],"bound":[212],"values":[213],"ranging":[214],"from":[215],"BOUND~1":[216],"BOUND~2000.":[218],"While":[219],"at":[220],"BOUND~1,":[221],"branches":[225],"100\\%":[227],"PPO-LLM":[229],"PALS":[232,257],"suite,":[233],"comparison,":[235],"around":[238],"86.8\\%":[239],"kS-LLM++.":[241],"This":[242],"confirms":[243],"adaptive":[245],"driven":[248],"substantially":[251],"static":[253],"strategies":[255],"type":[258],"programs.":[259]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-06T00:00:00"}