# The RSI Tax: When Recursive Self-Improvement Is Not Worth the Cost

**Authors:** Yitong Zhang, Ang Li, Yisen Wang  
**Published:** 10 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.13524) · [PDF](https://arxiv.org/pdf/2611.13524) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.13524.html)

## Abstract

Recursive self-improvement (RSI) seeks to improve an agent using its own task experience. Its practical value depends on whether performance gains justify the full cost of self-improvement and task execution. We evaluate this trade-off on continual task streams, scoring each task before its feedback is used for subsequent updates. We define the \emph{RSI Tax} as the token cost of the self-improvement process and include it alongside task-execution costs in end-to-end evaluation. Across six methods and two language models, a bounded-note baseline matches or exceeds the observed accuracy of Meta-Harness, EvoSkill, and RRSI, with mean total-token savings of 65.6-71.0\%. We decompose the RSI Tax into verification, exploration, and writing costs, and track subsequent use of the associated state or artifact. For these three RSI methods, verification accounts for 74.8--93.6% of the aggregate RSI Tax. A substantial share of the RSI Tax is also associated with states or artifacts that are not used later in the evaluated streams. These results expose a practical limitation of costly RSI procedures: improvements in the deployed agent need not justify the expense of the improvement process. They motivate RSI objectives that jointly optimize the RSI Tax and expected task-execution cost while ensuring continued growth in agent capabilities across the task stream.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.