نسخة أولية وصول مفتوح
Dyad: Extending Large Language Models with Native Typed Decision-Making
We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dyad, an architecture that augments a pretrained LLM with an environment-conditioned action encoder that embeds each candidate action description in parallel, then scores t …