# Preprint proposes rule-based shortcut for routine LLM-agent actions

_Tuesday, August 18, 2026 at 12:00 AM EDT · AI, Science · Latest · Tier 2 — Notable_

A preprint describes HaReCAP, an extension to the ReCAP recursive agent framework that compiles frequent successful leaf-level decisions into one-step rules. During use, the system skips an LLM call only when a rule uniquely selects a legal action; otherwise it reverts to ReCAP. Tests using Qwen3.5-27B on Robotouille and ALFWorld reported token-consumption reductions of 14.67%, 17.93%, and 20.08% respectively among tasks solved by both systems. The work characterizes the rules as auditable and able to abstain.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2608.16447)

---
Canonical: https://techandbusiness.org/newswire/abkMRJ4gR2nuvjp0eMv-P5
Retrieved: 2026-08-18T09:24:17.789Z
Publisher: Tech & Business (techandbusiness.org)