[2605.01920] A Language for Describing Agentic LLM Contexts

-->

Computer Science > Artificial Intelligence

arXiv:2605.01920 (cs)

[Submitted on 3 May 2026]

Title:A Language for Describing Agentic LLM Contexts

Authors:Noga Peleg Pelc, Gal A. Kaminka, Yoav Goldberg<br>View a PDF of the paper titled A Language for Describing Agentic LLM Contexts, by Noga Peleg Pelc and 2 other authors

View PDF<br>HTML (experimental)

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 this http URL.

Comments:<br>18 pages, 12 figures. Accepted at CAIS '26. Project page: this http URL

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA); Software Engineering (cs.SE)

ACM classes:<br>I.2.7; I.2.11; D.3.2

Cite as:<br>arXiv:2605.01920 [cs.AI]

(or<br>arXiv:2605.01920v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.01920

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Journal reference:<br>CAIS '26: ACM Conference on AI and Agentic Systems, May 2026, San Jose, CA, USA

Related DOI:

https://doi.org/10.1145/3786335.3813126

Focus to learn more

DOI(s) linking to related resources

Submission history<br>From: Noga Peleg Pelc [view email]<br>[v1]<br>Sun, 3 May 2026 15:02:44 UTC (2,710 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled A Language for Describing Agentic LLM Contexts, by Noga Peleg Pelc and 2 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-05

Change to browse by:

cs<br>cs.CL<br>cs.MA<br>cs.SE

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs...