Bidirectional transparency in human-agent communications: effects of direction and level of transparency.

This study investigated whether bidirectional transparency, compared to agent-to-human transparency, improved human–agent collaboration. Additionally, we examined the optimal transparency levels for both humans and agents. We assessed the impact of transparency direction and level on various metrics...

Descripción completa

Detalles Bibliográficos
Publicado en:Ergonomics Vol. 69; no. 2; pp. 187 - 206
Autores principales: Xu, Xinran, Yu, Ruifeng, Yuan, Minhui, Zheng, Jingyue
Formato: research tables/charts Journal Article
Publicado: Taylor & Francis Ltd Feb2026
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=191012016&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 191012016
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00140139
        ERO
      jtl: Ergonomics
      issn: 00140139
      maglogo: Y
    pubinfo:
      dt: Feb2026
      vid: 69
      iid: 2
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        191012016
        182530750
        191012016
        191012016
        10.1080/00140139.2025.2456535
        191012016
      ppf: 187
      ppct: 19
      formats:
      tig:
        atl: Bidirectional transparency in human-agent communications: effects of direction and level of transparency.
      aug:
        au:
          Xu, Xinran
          Yu, Ruifeng
          Yuan, Minhui
          Zheng, Jingyue
        affil: Department of Industrial Engineering, Tsinghua University, Beijing, China
      sug:
        subj:
          Artificial Intelligence
          User-Computer Interface
          Communication
          Cooperative Behavior
          Task Performance and Analysis
          Human
          Male
          Female
          Adult
          Experimental Studies
          Trust
          Decision Support Techniques
          Models, Theoretical
          Simulations
          Workload
          Cognition
          Computer Simulation
          Paired T-Tests
          Analysis of Variance
          Post Hoc Analysis
          Statistical Significance
          Data Analysis Software
          Descriptive Statistics
          Funding Source
          Adult: 19-44 years
          Male
          Female
      ab: This study investigated whether bidirectional transparency, compared to agent-to-human transparency, improved human–agent collaboration. Additionally, we examined the optimal transparency levels for both humans and agents. We assessed the impact of transparency direction and level on various metrics of a human-agent team, including performance, trust, satisfaction, perceived agent's teaming skills, and mental workload. A total of 30 participants engaged in a human-agent collaborative game in a within-subject experiment with five conditions: a 2 (transparency directions: agent-to-human transparency vs. bidirectional transparency) × 2 (transparency levels: reasoning transparency vs. reasoning + projection transparency) factorial design, plus an additional action transparency condition as a control condition. The findings indicated that bidirectional transparency improved task performance without increasing the mental workload. This study recommends a bidirectional transparency mechanism, in which the agent provides transparency to humans regarding its reasoning and predictions, whereas humans offer transparency to the agent regarding their reasoning. Practitioner Summary: This study highlights the importance of bidirectional transparency in human-agent collaboration, demonstrating its effectiveness in enhancing task performance without increasing mental workload. It recommends implementing a mechanism where both humans and agents share transparency information, optimising collaboration outcomes.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N