Dyad: Extending Large Language Models with Native Typed Decision-Making
Dyad is introduced, an architecture that augments a pretrained LLM with an environment-conditioned action encoder that embeds each candidate action description in parallel, then scores these embeddings against the LLM's internal state to yield a distribution over typed actions.
Yundaichuan Zhan, Wei-Shi Wang, Wen-Biao Liu et al.
· 0 citations