A Language for Describing Agentic LLM Contexts
The paper introduces the Agentic Context Description Language (ACDL), designed to specify the structure and dynamics of input contexts for large language models (LLMs). ACDL aims to standardize how LLM contexts are described, addressing the lack of formal methods in the field. The authors encourage the adoption of ACDL for clearer communication and documentation within the AI community.
- ▪ACDL provides a precise and readable way to describe LLM input contexts.
- ▪The language includes constructs for role message sequences, dynamic content, and conditional structures.
- ▪The authors demonstrate ACDL by documenting existing systems and variants.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2605.01920 |
| Publication time | Sun, 24 May 2026 20:31:30 +0000 |
| Retrieval time | 2026-05-24T20:37:34.510Z |
| Last seen | 2026-05-24T20:37:34.510Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | YIyy3t5MnK1L |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
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 View a PDF of the paper titled A Language for Describing Agentic LLM Contexts, by Noga Peleg Pelc and 2 other authors View PDF 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
