A Language for Describing Agentic LLM Contexts
Noga Peleg Pelc, Gal A. Kaminka, Yoav Goldberg
Why It Matters
What makes this one worth your time
Standardizing context representation can enhance communication and understanding among researchers and engineers working with LLMs, potentially improving system design and collaboration.
ACDL offers a standardized way to describe and visualize LLM input contexts.
Summary
The paper introduces the Agentic Context Description Language (ACDL), a formal language designed to specify and visualize the structure and dynamics of input contexts for LLM agents, addressing the lack of standardization in context representation.
Key contributions
- Introduction of the Agentic Context Description Language (ACDL) for LLM context specification.
- Provision of visualizations for context representation.
- Documentation of existing systems using ACDL to demonstrate its applicability.
Notable insights
- ACDL allows for both informal and formal representations of context, making it versatile for different use cases.
- The language captures dynamic aspects of context evolution, which is crucial for developing more sophisticated LLM agents.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2605.01920v1 Announce Type: new Abstract: Large language models are increasingly used within larger systems ("LLM agents"). These make a sequence of LLM calls, each call providing the LLM with a combination of instructions, observations, and interaction history. The design of the encoded information and its structure play a central role in the quality of the resulting system, leading to efforts spent on context engineering. It is therefore critical to communicate the composition of the LLM context in a system, and how it evolves over time. Yet, no standard exists for doing so: context construction is typically conveyed through informal prose, ad hoc diagrams, or direct inspection of code, none of which precisely capture how a prompt evolves across interaction steps or how two context representation strategies differ. To remedy this, we introduce the Agentic Context Description Language (ACDL), a language for specifying the structure and dynamics of LLM input contexts in a precise, readable, and standard manner, along with visualizations. ACDL provides constructs for specifying context aspects such as role message sequences, dynamic content, time-indexed references, and conditional or iterative structure, capturing the full architecture of a prompt independently of any particular implementation. ACDL diagrams can be hand drawn on a whiteboard, or written in formal language which can then be rendered. We describe the language, demonstrate it by documenting several existing systems and their variants, and encourage the community to adopt it for describing LLM systems context, both in day-to-day communication and in papers. Tooling, examples and documentation are available at www.acdlang.org.