{"id":"https://openalex.org/W7166842850","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1240","title":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","display_name":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166842850","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1240"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1240","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1240","pdf_url":"https://aclanthology.org/2026.findings-acl.1240.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.1240.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093784797","display_name":"Lingrui Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingrui Mei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677836","display_name":"Shenghua Liu","orcid":"https://orcid.org/0000-0003-2120-3598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenghua Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139804582","display_name":"Yiwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiwei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094348722","display_name":"Baolong Bi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baolong Bi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139768217","display_name":"Yuyao Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyao Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139829104","display_name":"Jun Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139834637","display_name":"Yurong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yurong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139812510","display_name":"Xueqi Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7896071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24761","last_page":"24786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.08269999921321869,"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":0.08269999921321869,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.04899999871850014,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.04399999976158142,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/scaling","display_name":"Scaling","score":0.35420000553131104},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.2888999879360199},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.28439998626708984},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27469998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4722999930381775},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.27480000257492065},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2703000009059906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1240","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1240","pdf_url":"https://aclanthology.org/2026.findings-acl.1240.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.1240","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1240","pdf_url":"https://aclanthology.org/2026.findings-acl.1240.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":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.6442184448242188}],"awards":[{"id":"https://openalex.org/G1907283378","display_name":null,"funder_award_id":"62441229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2706053043","display_name":null,"funder_award_id":"62377043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8808570173","display_name":null,"funder_award_id":"U25B2076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166842850.pdf","grobid_xml":"https://content.openalex.org/works/W7166842850.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"made":[5],"remarkable":[6],"breakthroughs":[7],"in":[8,138],"reasoning,":[9],"yet":[10],"continue":[11],"to":[12,20,126,150],"struggle":[13],"with":[14,73,98,146],"hallucinations,":[15],"logical":[16],"errors,":[17,74],"and":[18,75,89],"inability":[19],"self-correct":[21],"during":[22],"complex":[23],"multi-step":[24],"tasks.Current":[25],"approaches":[26],"like":[27,115],"chain-of-thought":[28],"prompting":[29],"offer":[30],"limited":[31],"reasoning":[32,52,60,81],"capabilities":[33],"that":[34,49],"fail":[35],"when":[36,71],"precise":[37],"step":[38],"validation":[39],"is":[40],"required.We":[41],"propose":[42],"Environment":[43],"Augmented":[44],"Generation":[45],"(EAG),":[46],"a":[47],"framework":[48],"enhances":[50],"LLM":[51],"through:":[53],"(1)":[54],"real-time":[55],"environmental":[56],"feedback":[57,97],"validating":[58],"each":[59],"step,":[61],"(2)":[62],"dynamic":[63],"branch":[64],"exploration":[65],"for":[66],"investigating":[67],"alternative":[68],"solution":[69],"paths":[70],"faced":[72],"(3)":[76],"experience-based":[77],"learning":[78],"from":[79],"successful":[80],"trajectories.Unlike":[82],"existing":[83],"methods,":[84],"EAG":[85],"enables":[86],"deliberate":[87],"backtracking":[88],"strategic":[90],"replanning":[91],"through":[92],"tight":[93],"integration":[94],"of":[95],"execution":[96],"branching":[99],"exploration.Our":[100],"a1-32B":[101],"model":[102],"achieves":[103],"state-of-the-art":[104],"performance":[105,144],"among":[106],"similar-sized":[107],"models":[108,114,123],"across":[109],"all":[110],"benchmarks,":[111],"matching":[112],"larger":[113],"o1":[116],"on":[117],"competition":[118],"mathematics":[119],"while":[120],"outperforming":[121],"comparable":[122],"by":[124],"up":[125],"24.4":[127],"percentage":[128],"points.Analysis":[129],"reveals":[130],"EAG's":[131],"distinctive":[132],"scaling":[133],"pattern:":[134],"initial":[135],"token":[136],"investment":[137],"environment":[139],"interaction":[140],"yields":[141],"substantial":[142],"longterm":[143],"dividends,":[145],"advantages":[147],"amplifying":[148],"proportionally":[149],"task":[151],"complexity.":[152]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
