Revisiting Human-Agent Communication: The Importance of Joint Co-construction and Understanding Mental States
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
The study of human-human communication and the development of computational models for human-agent communication have diverged significantly throughout the last decade. Yet, despite frequently made claims of “super-human performance” in, e.g., speech recognition or image processing, so far, no system is able to lead a half-decent coherent conversation with a human. In this paper, we argue that we must start to re-consider the hallmarks of cooperative communication and the core capabilities that we have developed for it, and which conversational agents need to be equipped with: incremental joint co-construction and mentalizing. We base our argument on a vast body of work on human-human communication and its psychological processes that we reason to be relevant and necessary to take into account when modeling human-agent communication. We contrast those with current conceptualizations of human-agent interaction and formulate suggestions for the development of future systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452 · cited 1×
“Building computer systems that are able to converse autonomously and coherently with a human is a long-standing goal of Artificial Intelligence and Human-Computer Interaction (going back, at least, to the seminal Eliza system presented by Weizenbaum, 1966).”
BackgroundMachines and Mindlessness: Social Responses to Computers
Nass, C., & Moon, Y. (2000) · Journal of Social Issues · doi:10.1111/0022-4537.00153 · Cited by 4,022 · cited 1×
“…each other cognitively or affectively, it can be expected based on findings related to media equation assumptions (Reeves and Nass, 1996; Nass and Moon, 2000; Krämer, 2005) that humans display “normal” behavior in the sense of deeply-rooted social and communicative actions toward…”
BackgroundA survey of socially interactive robots
Fong, T., Nourbakhsh, I., & Dautenhahn, K. (2003) · Robotics and Autonomous Systems · doi:10.1016/s0921-8890(02)00372-x · Cited by 3,162 · cited 1×
“Corresponding abilities have been investigated for spoken dialog systems (McTear, 2002), embodied conversational agents (Cassell et al., 2000) and sociable robots (Fong et al., 2003) that are embodied and can also produce nonverbal behavior (e.g., gestures, facial displays, and gaze).”
BackgroundDevelopment and neurophysiology of mentalizing
Frith, U., & Frith, C. D. (2003) · Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences · doi:10.1098/rstb.2002.1218 · Cited by 2,306 · cited 1×
“In recent years, ToM has been discussed as a basic prerequisite for HHI and various terms have been established: mentalizing (Frith and Frith, 2003), mindreading (Baron-Cohen, 1995), and intentional stance (Dennett, 1987) all basically refer to the same ability that is seen as crucial for all…”
BackgroundClark, H. H., & Schaefer, E. F. (1989) · Cognitive Science · doi:10.1207/s15516709cog1302_7 · Cited by 1,699
Vinyals, O., & Le, Q. (2015) · arXiv · doi:10.48550/arxiv.1506.05869 · Cited by 1,400
From Eliza to XiaoIce: Challenges and opportunities with social chatbots
Shum, H.-Y., He, X.-D., & Li, D. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1700826 · Cited by 749 · cited 1×
“…only respond to users’ specific questions or commands in natural language (spoken or typed), but also to establish a connection by tracking the user’s emotional state (Li et al., 2018) and satisfying users’ social needs for communication, affection, entertainment, or belonging (Shum et al., 2018).”
BackgroundA Survey on Dialogue Systems: Recent Advances and New Frontiers
Chen, H., Liu, X., Yin, D., & Tang, J. (2017) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3166054.3166058 · Cited by 579
Spoken dialogue technology: enabling the conversational user interface
McTear, M. F. (2002) · ACM Computing Surveys · doi:10.1145/505282.505285 · Cited by 571
Cited by
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315
A multifaceted vision of the human-AI collaboration: a comprehensive review
Puerta-Beldarrain, M., Gómez-Carmona, O., Sánchez-Corcuera, R., Casado-Mansilla, D., López-de-Ipiña, D., & Chen, L. (2025) · IEEE Access · doi:10.1109/access.2025.3536095 · Cited by 73
“Similarly, Koop et al. apply principles of human-to-human communication as the foundation for developing effective human-AI interactions [341].”
Mavrina, L., Szczuka, J., Strathmann, C., Bohnenkamp, L. M., Krämer, N., & Kopp, S. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2022.791704 · Cited by 43
Self-citation“Pepper, what do you mean?” Miscommunication and repair in robot-led survey interaction
Stommel, W., de Rijk, L., & Boumans, R. (2022) · 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/ro-man53752.2022.9900528 · Cited by 19
“Lastly, our findings seem to support the claim that social robots and voice agents are unable to lead “a half-decent coherent conversation with a human” [37] when it comes to miscommunication and repair, but for health surveys some nuance seems in place.”
ResultRefocusing on Relevance: Personalization in NLG
Dudy, S., Bedrick, S., & Webber, B. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.421 · Cited by 17
“…in their infancy with regards to personalization; in a recent work discussing aspects of human-computer interaction in relation to dialogue systems, Kopp and Krämer (2021) suggest that the field should “(re-)emphasize the hallmarks of human communication and its complexity, and ... argue that we…”
Background
Metadata
- Authors
- Kopp, S., & Krämer, N.
- Venue
- Frontiers in Psychology
- Publisher
- Frontiers Media SA
- Published
- 2021-03-23
- Volume
- 12
- Pages
- 580955-580955
- ISSN
- 1664-1078 (ISSN-L)
- OpenAlex
- W3136983296
- Cited by
- 47
- References
- 17
- FWCI
- 3.18
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Revisiting Human-Agent Communication: The Importance of Joint Co-construction and Understanding Mental States. https://app.cochat.ai/papers/10.3389/fpsyg.2021.580955
- The paper
- Kopp, S., & Krämer, N. (2021). Revisiting Human-Agent Communication: The Importance of Joint Co-construction and Understanding Mental States. Frontiers in Psychology. https://doi.org/10.3389/fpsyg.2021.580955
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.