{"id":"https://openalex.org/W7166859258","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1350","title":"TRM-Planner: Offline Target Planning and Distillation for Tiny Recursive Models","display_name":"TRM-Planner: Offline Target Planning and Distillation for Tiny Recursive Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166859258","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1350"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1350","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1350","pdf_url":"https://aclanthology.org/2026.findings-acl.1350.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.1350.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130760480","display_name":"Euijin Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Euijin Baek","raw_affiliation_strings":["University of Alberta University of Waikato Mi-Young Kim University of Alberta University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta University of Waikato Mi-Young Kim University of Alberta University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139659235","display_name":"Housam Babiker","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Housam Babiker","raw_affiliation_strings":["University of Alberta University of Waikato Mi-Young Kim University of Alberta University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta University of Waikato Mi-Young Kim University of Alberta University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135100208","display_name":"Mi-Young Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mi-Young Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139812169","display_name":"Randy Goebel","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Randy Goebel","raw_affiliation_strings":["University of Alberta University of Waikato Mi-Young Kim University of Alberta University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta University of Waikato Mi-Young Kim University of Alberta University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.83696595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27058","last_page":"27070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.6948000192642212,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.6948000192642212,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.026599999517202377,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.020400000736117363,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3400000035762787},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.33379998803138733},{"id":"https://openalex.org/keywords/fractionating-column","display_name":"Fractionating column","score":0.28519999980926514},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2694999873638153},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.257099986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.583299994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C154030694","wikidata":"https://www.wikidata.org/wiki/Q1436074","display_name":"Fractionating column","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26350000500679016},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1350","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1350","pdf_url":"https://aclanthology.org/2026.findings-acl.1350.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.1350","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1350","pdf_url":"https://aclanthology.org/2026.findings-acl.1350.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":[{"id":"https://openalex.org/G2614460161","display_name":null,"funder_award_id":"-2022","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3986691484","display_name":"Theoretical Particle Physics","funder_award_id":"crc-2022-00346","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320314212","display_name":"Alberta Machine Intelligence Institute","ror":null},{"id":"https://openalex.org/F4320319946","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27"},{"id":"https://openalex.org/F4320325651","display_name":"Alberta Innovates","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166859258.pdf","grobid_xml":"https://content.openalex.org/works/W7166859258.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tiny":[0],"Recursive":[1],"Models":[2],"(TRMs)":[3],"perform":[4],"iterative":[5],"reasoning":[6],"with":[7,86,117],"an":[8,47,104],"Adaptive":[9],"Computation":[10],"Time":[11],"(ACT)-style":[12],"loop,":[13],"but":[14],"their":[15,28],"effective":[16],"supervision":[17],"can":[18,31],"be":[19,32],"target-sensitive":[20],"to":[21,34,46],"refinement":[22,58],"depth":[23],"and":[24,27,60,78,100,127],"halting":[25,29],"calibration,":[26],"behavior":[30],"difficult":[33],"tune.We":[35],"introduce":[36],"TRM-Planner,":[37],"a":[38,68,92],"two-stage":[39],"teachercache":[40],"distillation":[41,93],"recipe":[42],"that":[43],"shifts":[44],"compute":[45],"offline":[48],"teacher-cache":[49],"stage.A":[50],"frozen":[51],"TRM":[52,82,89,109],"checkpoint":[53],"is":[54,83],"unrolled":[55],"for":[56,63],"multiple":[57],"steps":[59],"stochastic":[61],"rollouts;":[62],"each":[64],"instance":[65],"we":[66],"cache":[67],"small":[69],"set":[70],"of":[71],"teacher":[72],"entries":[73],"(tokens,":[74],"logits,":[75],"step":[76],"index,":[77],"quality":[79],"metadata).A":[80],"student":[81],"then":[84],"trained":[85],"the":[87,120],"standard":[88],"objective":[90],"plus":[91],"loss":[94],"computed":[95],"from":[96,125],"cached":[97],"entries.Across":[98],"Sudoku-Extreme":[99],"ARC-AGI-1/2,":[101],"TRM-Planner":[102],"shows":[103],"improvement":[105],"over":[106],"our":[107],"reproduced":[108],"baseline":[110],"while":[111],"leaving":[112],"studenttime":[113],"inference":[114],"unchanged.On":[115],"ARC1/ARC2":[116],"7M":[118],"parameters,":[119],"two-attempt":[121],"accuracy":[122],"(pass@2)":[123],"increases":[124],"43.1%\u219248.1%":[126],"6.7%\u21929.2%,respectively.":[128]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2026-07-02T00:00:00"}