Researchers Launch ACD Language To Standardize AI Agent Contexts

our language, ACDL (agent context description language) makes it easy to describe the structural semantic composition of an agentic prompt as it evolves over time. for example, here is ReAct context with tools at the end and history that includes reasoning traces:

one thing that keeps coming up when working on agents, is trying to describe to each other (and to a coding agent) how their context is structured, and how it evolves over time. we created a language to fix that.

check out @noga2p 's thread, and also https://acdlang.org

and this is a simple RAG context, where each query is fully independent from the previous ones (fresh context)

we have been using ACDL internally in our group for some time now, and i found it to be really helpful when talking about agents and their implementation. and documenting the context in ACDL many times makes you understand it better.