Iris: A Conversational Agent for Complex Tasks
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Today, most conversational agents are limited to simple tasks supported by standalone commands, such as getting directions or scheduling an appointment. To support more complex tasks, agents must be able to generalize from and combine the commands they already understand. This paper presents a new approach to designing conversational agents inspired by linguistic theory, where agents can execute complex requests interactively by combining commands through nested conversations. We demonstrate this approach in Iris, an agent that can perform open-ended data science tasks such as lexical analysis and predictive modeling. To power Iris, we have created a domain-specific language that transforms Python functions into combinable automata and regulates their combinations through a type system. Running a user study to examine the strengths and limitations of our approach, we find that data scientists completed a modeling task 2.6 times faster with Iris than with Jupyter Notebook.
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
Searle, J. R. (1969) · doi:10.1017/cbo9781139173438 · Cited by 11,718
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×
“As early as 1964, Joseph Weizenbaum demonstrated how a computer program could hold open-ended conversations us-ing a large set of pattern matching rules [45].”
BackgroundAn Introduction to Discourse Analysis
Gee, J. P. (2014) · doi:10.4324/9781315819679 · Cited by 1,036
Empath: Understanding Topic Signals in Large-Scale Text
Fast, E., Chen, B., & Bernstein, M. S. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858535 · Cited by 413
Self-citationSuede: a Wizard of Oz prototyping tool for speech user interfaces
Klemmer, S. R., Sinha, A. K., Chen, J., Landay, J. A., Aboobaker, N., & Wang, A. (2000) · Proceedings of the 13th annual ACM symposium on User interface software and technology - UIST '00 · doi:10.1145/354401.354406 · Cited by 230
Multimodal error correction for speech user interfaces
Suhm, B., Myers, B., & Waibel, A. (2001) · ACM Transactions on Computer-Human Interaction · doi:10.1145/371127.371166 · Cited by 198 · cited 1×
“DataTone and PixelTone provide guidance here, illustrating how systems can be designed to surface decisions about ambiguity [11] (at a point where these decisions matter), and constrain some of these decisions by direct manipulation [21] or other modalities [42].”
BackgroundLearning Language Games through Interaction
Wang, S. I., Liang, P., & Manning, C. D. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1224 · Cited by 132
Gestalt: integrated support for implementation and analysis in machine learning
Patel, K., Bancroft, N., Drucker, S. M., Fogarty, J., Ko, A. J., & Landay, J. (2010) · Proceedings of the 23nd annual ACM symposium on User interface software and technology · doi:10.1145/1866029.1866038 · Cited by 112 · cited 1×
“provide a framework (through its DSL and command API) that allows others to more quickly design conversational agents. Iris also draws on insights from tools designed to help with data science tasks [34, 44, 41]. Wrangler, for example, combines spreadsheet visualizations with natural language command descriptions to h…”
BackgroundCalendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop
Cranshaw, J., Elwany, E., Newman, T., Kocielnik, R., Yu, B., Soni, S., Teevan, J., & Monroy-Hernández, A. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025780 · Cited by 106 · cited 1×
“A second class of work has turned a practical lens on the challenges of implementing speech interfaces, providing tools for rapid prototyping [23], triggering user queries [49], or extending the limits of machine reasoning with a crowd [6, 25, 26].”
Background
Cited by
Reicherts, L., Rogers, Y., Capra, L., Wood, E., Duong, T. D., & Sebire, N. (2022) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3484221 · Cited by 52
How Knowledge Workers Use and Want to Use LLMs in an Enterprise Context
Brachman, M., El-Ashry, A., Dugan, C., & Geyer, W. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650841 · Cited by 37
The IBM natural conversation framework: a new paradigm for conversational UX design
Moore, R. J., An, S., & Ren, G.-J. (2023) · Human–Computer Interaction · doi:10.1080/07370024.2022.2081571 · Cited by 26
“All conversational user interfaces seem to return natural-language content to users, but they vary in terms of the granularity of that content from phrases or sentences to document-style paragraphs to documents (Fast et al., 2018; Guo et al., 2018; Liao et al., 2017).”
BackgroundVIVID: Human-AI Collaborative Authoring of Vicarious Dialogues from Lecture Videos
Choi, S., Lee, H., Lee, Y., & Kim, J. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642867 · Cited by 17
“Thus,research has employed a Conversational Agent (CA) [25, 31, 37, 60, 72] to simulate interactions between a virtual tutor and tutee for supporting vicarious learners in video-based learning.”
Narrative Player: Reviving Data Narratives With Visuals
Shao, Z., Shen, L., Li, H., Shan, Y., Qu, H., Wang, Y., & Chen, S. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3530512 · Cited by 15
“They have developed interactive dialogue systems for direct visualization interaction [53], complex request and simultaneous conversations handling [19], and visualization authoring [72], alongside exploring design principles for NLI-based data exploration [70].”
Method
Metadata
- Authors
- Fast, E., Chen, B., Mendelsohn, J., Bassen, J., & Bernstein, M. S.
- Venue
- Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2018-04-21
- Pages
- 1-12
- OpenAlex
- W2963967828
- Cited by
- 108
- References
- 9
- FWCI
- 5.41
- Type
- conference paper
- Language
- en
- Open access
- closed
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: Iris: A Conversational Agent for Complex Tasks. https://app.cochat.ai/papers/10.1145/3173574.3174047
- The paper
- Fast, E., Chen, B., Mendelsohn, J., Bassen, J., & Bernstein, M. S. (2018). Iris: A Conversational Agent for Complex Tasks. Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3173574.3174047
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.