Improvisational Games as a Benchmark for Social Intelligence of AI Agents: The Case of Connections

View PDF HTML (experimental)

Abstract:We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills in knowledge retrieval, summarization and awareness of cognitive states of other agents. We show how the game serves as a good benchmark for social intelligence abilities of language model based agents that go beyond the agents' own memory and deductive reasoning and also involve gauging the understanding capabilities of other agents. Finally, we show how through communication with other agents in a constrained environment, AI agents must demonstrate social awareness and intelligence in games involving collaboration.

Comments: this https URL

Subjects:

Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)

Cite as: arXiv:2604.00284 [cs.AI]

(or arXiv:2604.00284v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2604.00284

arXiv-issued DOI via DataCite (pending registration)

Journal reference: https://wordplay-workshop.github.io/wordplay2024/pdfs/16.pdf

Submission history

From: Gaurav Rajesh Parikh [view email] [v1] Tue, 31 Mar 2026 22:16:25 UTC (67 KB)