# Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback

**Published:** October 9, 2026
**Author:** Zexuan Liu, Yuning Yang, Tiancheng Zhao
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/curating-always-loaded-context-for-llm-agents-a-capacitated-assortment-m

At the start of every session, LLM agents load a fixed context file, such as $\texttt{AGENTS.md}$. Each loaded token in the file is charged again in every later round of the session, and these files can degrade performance as they grow in size. However, in practice, human or…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.11007)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*