{"id":"https://openalex.org/W7101718751","doi":"https://doi.org/10.48550/arxiv.2510.22907","title":"Reinforcement Learning from Compiler and Language Server Feedback","display_name":"Reinforcement Learning from Compiler and Language Server Feedback","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7101718751","doi":"https://doi.org/10.48550/arxiv.2510.22907"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2510.22907","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.22907","pdf_url":"https://arxiv.org/pdf/2510.22907","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.22907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157952676","display_name":"Yifan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yifan","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":null,"display_name":"Contributors, Lanser","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Contributors, Lanser","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20089843"],"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":true,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9945999979972839,"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":0.9945999979972839,"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":0.0017000000225380063,"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/T10533","display_name":"Teaching and Learning Programming","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/ai-coding-agents","display_name":"coding agents","score":0.8640000224113464},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.7459999918937683},{"id":"https://openalex.org/keywords/compiler-feedback","display_name":"compiler feedback","score":0.703000009059906},{"id":"https://openalex.org/keywords/language-server-protocol","display_name":"Language Server Protocol","score":0.8650000095367432},{"id":"https://openalex.org/keywords/type-checking","display_name":"type checking","score":0.5130000114440918},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.5509999990463257},{"id":"https://openalex.org/keywords/deterministic-replay","display_name":"deterministic replay","score":0.33899998664855957},{"id":"https://openalex.org/keywords/ci-cd","display_name":"CI/CD","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968000173568726},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C20724563","wikidata":"https://www.wikidata.org/wiki/Q3075258","display_name":"Language primitive","level":4,"score":0.3822000026702881},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C164554305","wikidata":"https://www.wikidata.org/wiki/Q71550","display_name":"Application server","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C204156049","wikidata":"https://www.wikidata.org/wiki/Q751436","display_name":"Inter-process communication","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2776411971","wikidata":"https://www.wikidata.org/wiki/Q17141398","display_name":"Sublanguage","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C152880691","wikidata":"https://www.wikidata.org/wiki/Q146813","display_name":"Client\u2013server model","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C2777742743","wikidata":"https://www.wikidata.org/wiki/Q19904005","display_name":"Durvalumab","level":5,"score":0.2524000108242035},{"id":"https://openalex.org/C2780512708","wikidata":"https://www.wikidata.org/wiki/Q850661","display_name":"XQuery","level":4,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.22907","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.22907","pdf_url":"https://arxiv.org/pdf/2510.22907","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.2510.22907","doi":"https://doi.org/10.48550/arxiv.2510.22907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.22907","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.22907","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.22907","pdf_url":"https://arxiv.org/pdf/2510.22907","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":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.524727463722229}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7101718751.pdf","grobid_xml":"https://content.openalex.org/works/W7101718751.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Coding":[0],"agents":[1,88],"fail":[2],"when":[3],"text-level":[4],"guesses":[5],"outrun":[6],"program":[7],"facts:":[8],"they":[9],"hallucinate":[10],"APIs,":[11],"drift":[12],"to":[13,87],"the":[14,23,35,40,177],"wrong":[15],"symbol,":[16],"and":[17,30,49,71,89,99,112,130,150,168],"apply":[18],"edits":[19],"without":[20],"evidence":[21],"that":[22,83,140,170],"workspace":[24],"remains":[25],"valid.":[26],"Compilers,":[27],"type":[28,46],"checkers,":[29],"language":[31],"servers":[32],"already":[33],"compute":[34],"missing":[36],"supervision":[37,189],"signal,":[38],"in":[39,108,116,176],"form":[41],"of":[42,190],"diagnostics,":[43,109],"symbol":[44],"resolution,":[45],"information,":[47],"references,":[48],"refactoring":[50],"preconditions,":[51],"but":[52],"expose":[53],"it":[54],"through":[55],"interfaces":[56],"designed":[57],"for":[58,165,187],"human-driven":[59],"IDEs":[60],"rather":[61],"than":[62],"learning":[63],"loops.":[64],"We":[65,162],"introduce":[66],"Reinforcement":[67],"Learning":[68],"from":[69,105],"Compiler":[70],"Language":[72],"Server":[73],"Feedback":[74],"(RLCSF)":[75],"together":[76],"with":[77,126],"Lanser-CLI,":[78,115],"a":[79,97,101,151,184],"CLI-first":[80],"orchestration":[81],"layer":[82],"exposes":[84],"this":[85],"signal":[86],"CI.":[90],"RLCSF":[91],"treats":[92],"each":[93],"tool":[94],"interaction":[95],"as":[96],"transition":[98],"computes":[100],"shaped":[102],"process":[103,188],"reward":[104,152,175],"deterministic":[106,144],"changes":[107],"selector":[110],"confidence,":[111],"edit":[113],"safety.":[114],"turn,":[117],"converts":[118],"ephemeral":[119],"LSP":[120],"sessions":[121],"into":[122],"replayable":[123,158],"Analysis":[124],"Bundles":[125],"pinned":[127],"environment":[128],"metadata":[129],"stable":[131],"content":[132],"hashes.":[133],"Its":[134],"core":[135],"mechanisms":[136],"are":[137],"robust":[138],"selectors":[139],"go":[141],"beyond":[142],"file:line:col,":[143],"bundle":[145],"normalization,":[146],"preview-first":[147],"guarded":[148],"mutations,":[149],"functional":[153],"whose":[154],"potential-based":[155],"component":[156],"is":[157],"under":[159],"frozen":[160],"snapshots.":[161],"formalize":[163],"determinism":[164],"canonical":[166],"bundles":[167],"prove":[169],"componentwise-improving":[171],"transitions":[172],"receive":[173],"non-negative":[174],"undiscounted":[178],"setting.":[179],"Together,":[180],"these":[181],"pieces":[182],"yield":[183],"practical":[185],"substrate":[186],"coding":[191],"agents.":[192]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-29T00:00:00"}