{"id":"https://openalex.org/W7163410470","doi":"https://doi.org/10.48550/arxiv.2606.03135","title":"Uncertainty-Aware Clarification in LLM Agents with Information Gain","display_name":"Uncertainty-Aware Clarification in LLM Agents with Information Gain","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163410470","doi":"https://doi.org/10.48550/arxiv.2606.03135"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03135","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.2606.03135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137722656","display_name":"Mengyi Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Mengyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137785816","display_name":"Zhiwei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137729882","display_name":"Xin Li (51274)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137746317","display_name":"Tingyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Tingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137742081","display_name":"Ying Zhao","orcid":"https://orcid.org/0000-0003-0346-5631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137753216","display_name":"Zhijiang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Zhijiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137761220","display_name":"Wei Wang (17594)","orcid":"https://orcid.org/0000-0003-4088-5395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wei","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/T10028","display_name":"Topic Modeling","score":0.3619000017642975,"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/T10028","display_name":"Topic Modeling","score":0.3619000017642975,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.11060000211000443,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.09359999746084213,"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/ambiguity","display_name":"Ambiguity","score":0.7242000102996826},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6018000245094299},{"id":"https://openalex.org/keywords/information-gain","display_name":"Information gain","score":0.5562000274658203},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4374000132083893},{"id":"https://openalex.org/keywords/clarifier","display_name":"Clarifier","score":0.3804999887943268},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.35179999470710754},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3458000123500824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530999779701233},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7242000102996826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C2777428582","wikidata":"https://www.wikidata.org/wiki/Q17050939","display_name":"Clarifier","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2526000142097473},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03135","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.2606.03135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03135","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3,76],"agents":[4],"often":[5],"operate":[6],"under":[7],"underspecified":[8],"user":[9,15],"instructions,":[10],"where":[11],"latent":[12],"uncertainty":[13,91],"over":[14,129],"intent":[16],"leads":[17],"to":[18,40,80],"erroneous":[19],"tool":[20],"actions.":[21],"To":[22],"address":[23],"this":[24,78],"challenge,":[25],"we":[26],"propose":[27],"a":[28,48,105],"goal-oriented":[29],"clarification":[30,34,55,70],"framework":[31,103],"that":[32,50,87,119],"aligns":[33],"behavior":[35],"with":[36],"ambiguity":[37],"resolution.":[38],"Central":[39],"our":[41,102,120],"approach":[42],"is":[43],"the":[44,52,59,64,69,74,97,124,130],"Information":[45],"Gain":[46],"Reward,":[47],"metric":[49],"quantifies":[51],"utility":[53],"of":[54],"questions":[56],"by":[57,68,127],"measuring":[58],"Bayesian":[60],"belief":[61],"update":[62],"towards":[63],"ground-truth":[65],"goal":[66],"induced":[67],"exchange.":[71],"We":[72,100],"train":[73],"clarifier":[75],"using":[77],"reward":[79],"optimize":[81],"for":[82],"high":[83],"information":[84],"gain,":[85],"ensuring":[86],"clarifications":[88],"effectively":[89],"reduce":[90],"and":[92],"improve":[93],"task":[94],"completion":[95],"within":[96,104],"agent-tool-user":[98],"environment.":[99],"validate":[101],"clarification-enhanced":[106],"$\u03c4$-Bench":[107],"environment,":[108],"conducting":[109],"cross-agent":[110],"evaluations":[111],"across":[112],"five":[113],"heterogeneous":[114],"backbones.":[115],"Empirical":[116],"results":[117],"demonstrate":[118],"method":[121],"consistently":[122],"improves":[123],"success":[125],"rate":[126],"3.7\\%":[128],"no-clarification":[131],"baseline,":[132],"while":[133],"adding":[134],"only":[135],"0.3":[136],"total":[137],"interaction":[138],"steps":[139],"on":[140],"average.":[141]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}