Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we chat to AI pioneer, Michael Littman, learn about time-series forecasting for clinical data, investigate evolutionary game theory for cybersecurity, and get the scoop on neuromorphic computing. In the latest interview in our series meeting AI pioneers, Michael Littman reflects on the evolution of reinforcement learning, the power of science communication, and how generative AI is changing the way we teach and learn. Mayra Elwes is a PhD student developing machine learning methods for clinical time-series data. She is working on practical strategies to evaluate methods in a more contextualised way and on improving existing domain adaptation methods specific to time-series forecasting.

Communication between multiple language model (LM) agents has been shown to scale up the reasoning ability of LMs. While natural language has been the dominant medium for inter-LM communication, it is not obvious this should be the standard: not only does natural language communication incur high inference costs that scale quickly with the number of both agents and messages, but also the decoding process abstracts away too much rich information that could be otherwise accessed from the internal activations. In this work, we propose a simple technique whereby LMs communicate via activations; concretely, we pause an LM $\textit{B}$'s computation at an intermediate layer, combine its current activation with another LM $\textit{A}$'s intermediate activation via some function $\textit{f}$, then pass $\textit{f}$'s output into the next layer of $\textit{B}$ and continue the forward pass till decoding is complete. This approach scales up LMs on new tasks with zero additional parameters and data, and saves a substantial amount of compute over natural language communication. We test our method with various functional forms $\textit{f}$ on two experimental setups--multi-player coordination games and reasoning benchmarks--and find that it achieves up to $27.0\%$ improvement over natural language communication across datasets with $<$$1/4$ the compute, illustrating the superiority and robustness of activations as an alternative "language" for communication between LMs.

Utterance and Objective: Issues in Natural Language Communication

Also available in the ACM Digital LibraryCommunications of the ACM, 9 [#1]: 36-45