CPS-TaskForge: Generating Collaborative Problem Solving Environments for Diverse Communication Tasks
Nikita Haduong (1), Irene Wang, Bo-Ru Lu (1), Prithviraj Ammanabrolu, (2), Noah A. Smith (1, 3) ((1) Paul G. Allen School of Computer Science &, Engineering, University of Washington, (2) University of California, San, Diego, (3) Allen Institute for AI)

TL;DR
This paper introduces CPS-TaskForge, a flexible environment generator for collaborative problem solving research, enabling the study of larger teams and diverse communication tasks through configurable game-based scenarios.
Contribution
The paper presents CPS-TaskForge, a novel CPS environment generator and a design checklist to facilitate multi-agent CPS research and data collection.
Findings
Validated the generation of diverse natural language communication in CPS tasks.
Demonstrated the use of CPS-TaskForge for creating multi-agent problem solving environments.
Discussed future research opportunities with configurable CPS tasks.
Abstract
Teams can outperform individuals; could adding AI teammates further bolster performance of teams solving problems collaboratively? Collaborative problem solving (CPS) research commonly studies teams with two agents (human-human or human-AI), but team research literature finds that, for complex tasks, larger teams are more effective. Progress in studying collaboration with more than two agents, through textual records of team interactions, is hindered by a major data challenge: available CPS corpora are predominantly dyadic, and adapting pre-existing CPS tasks to more agents is non-trivial. We address this data challenge by developing a CPS task generator, CPS-TaskForge, that can produce environments for studying CPS under a wide array of conditions, and releasing a CPS task design checklist grounded in the theoretical PISA 2015 CPS framework to help facilitate the development of CPS…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInnovative Teaching and Learning Methods · Software Engineering Techniques and Practices
