cs.LGNov 10, 2026

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

Authors: Yitong Zhang, Ang Li, Yisen Wang

Organizations: School of Physics, Peking University · State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University

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 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.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. RSI-Env: An Open-Ended Environment for Recursive Self-Improvement of Agents

    Nov 1, 2026Wanying Qu, Zhiyuan Fan, Jiyao Liu +4LLM Agent Self-ImprovementRecursive Self-Improvement

  2. Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems

    Oct 12, 2026Xin Xu, Ke Cheng, Hao Wang +11LLM Agent Self-ImprovementRecursive Self-Improvement

  3. RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

    Sep 21, 2026Peng Xia, Rujun Han, Zifeng Wang +11OOD GeneralizationAgent Harness Optimization