{"id":"https://openalex.org/W7166841899","doi":"https://doi.org/10.18653/v1/2026.findings-acl.313","title":"Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction","display_name":"Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166841899","doi":"https://doi.org/10.18653/v1/2026.findings-acl.313"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.313","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.313","pdf_url":"https://aclanthology.org/2026.findings-acl.313.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.313.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139798665","display_name":"Xingwu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xingwu Chen","raw_affiliation_strings":["School of Computing and Data Science , The University of Hong Kong LIGHTSPEED"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science , The University of Hong Kong LIGHTSPEED","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758946","display_name":"Zhanqiu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhanqiu Zhang","raw_affiliation_strings":["School of Computing and Data Science , The University of Hong Kong LIGHTSPEED"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science , The University of Hong Kong LIGHTSPEED","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139733371","display_name":"Steven Y. Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Y. Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139784085","display_name":"Difan Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Difan Zou","raw_affiliation_strings":["School of Computing and Data Science , The University of Hong Kong LIGHTSPEED"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science , The University of Hong Kong LIGHTSPEED","institution_ids":["https://openalex.org/I889458895"]}]}],"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":0.84937682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6302","last_page":"6318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.1746000051498413,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.1746000051498413,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07649999856948853,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.06830000132322311,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42489999532699585},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3582000136375427},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3431999981403351},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.29980000853538513},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.29249998927116394},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2806999981403351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44760000705718994},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37310001254081726},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32580000162124634},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.313","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.313","pdf_url":"https://aclanthology.org/2026.findings-acl.313.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.313","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.313","pdf_url":"https://aclanthology.org/2026.findings-acl.313.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":[{"id":"https://metadata.un.org/sdg/10","score":0.5208053588867188,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166841899.pdf","grobid_xml":"https://content.openalex.org/works/W7166841899.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"LLMs":[1],"demonstrate":[2],"strong":[3,163],"reasoning":[4,63,88,144],"capabilities":[5,119],"when":[6,22,65],"provided":[7],"with":[8,84,96,131],"full":[9],"information":[10,23],"in":[11,19,41,73],"a":[12,39,55,100],"single":[13],"turn,":[14],"they":[15],"exhibit":[16],"substantial":[17],"vulnerability":[18],"multi-turn":[20,107,129],"interactions.Specifically,":[21],"is":[24],"revealed":[25],"incrementally":[26],"or":[27,70],"requires":[28],"updates,":[29],"models":[30,58,136],"frequently":[31],"fail":[32],"to":[33,38,44,61,81,105,124,137,168],"integrate":[34],"new":[35,71],"constraints,":[36],"leading":[37],"collapse":[40],"performance":[42],"compared":[43],"their":[45,143],"single-turn":[46],"baselines.We":[47],"term":[48],"the":[49,76,115,147],"root":[50],"cause":[51],"as":[52,120],"Contextual":[53],"Inertia:":[54],"phenomenon":[56],"where":[57],"rigidly":[59],"adhere":[60],"previous":[62,86],"traces.Even":[64],"users":[66],"explicitly":[67],"provide":[68,125],"corrections":[69],"data":[72],"later":[74],"turns,":[75],"model":[77],"ignores":[78],"them,":[79],"preferring":[80],"maintain":[82],"consistency":[83],"its":[85,178],"(incorrect)":[87],"path.To":[89],"address":[90],"this,":[91],"we":[92],"introduce":[93],"Reinforcement":[94],"Learning":[95],"Single-Turn":[97],"Anchors":[98],"(RLSTA),":[99],"generalizable":[101],"training":[102],"approach":[103],"designed":[104],"stabilize":[106],"interaction":[108],"across":[109],"diverse":[110],"scenarios":[111],"and":[112,141,157,170],"domains.RLSTA":[113],"leverages":[114],"model's":[116],"superior":[117],"singleturn":[118],"stable":[121],"internal":[122],"anchors":[123],"reward":[126],"signals.By":[127],"aligning":[128],"responses":[130],"these":[132],"anchors,":[133],"RLSTA":[134,152],"empowers":[135],"break":[138],"contextual":[139],"inertia":[140],"selfcalibrate":[142],"based":[145],"on":[146],"latest":[148],"information.Experiments":[149],"show":[150],"that":[151],"significantly":[153],"outperforms":[154],"standard":[155],"fine-tuning":[156],"abstention-based":[158],"methods.Notably,":[159],"our":[160],"method":[161],"exhibits":[162],"cross-domain":[164],"generalization":[165],"(e.g.,":[166],"math":[167],"code)":[169],"proves":[171],"effective":[172],"even":[173],"without":[174],"external":[175],"verifiers,":[176],"highlighting":[177],"potential":[179],"for":[180],"general-domain":[181],"applications.":[182]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2026-07-02T00:00:00"}