Modeling Communication to Coordinate Perspectives in Cooperation
This work addresses the challenge of overloaded signaling in AI and human cooperation, offering a novel computational account that could enhance communication in multi-agent systems, though it appears incremental in building on existing shared agency theories.
The paper tackles the problem of ambiguous communication in cooperative settings by proposing the Imagined We for Communication framework, which models how agents coordinate perspectives to achieve shared goals, and demonstrates through simulations that the model improves performance with deeper reasoning and outperforms baselines even at shallow levels.
Communication is highly overloaded. Despite this, even young children are good at leveraging context to understand ambiguous signals. We propose a computational account of overloaded signaling from a shared agency perspective which we call the Imagined We for Communication. Under this framework, communication helps cooperators coordinate their perspectives, allowing them to act together to achieve shared goals. We assume agents are rational cooperators, which puts constraints on how signals can be sent and interpreted. We implement this model in a set of simulations demonstrating this model's success under increasing ambiguity as well as increasing layers of reasoning. Our model is capable of improving performance with deeper recursive reasoning; however, it outperforms comparison baselines at even the shallowest level, highlighting how shared knowledge and cooperative logic can do much of the heavy-lifting in language.