cs.AINov 17, 2026

Values Shape What Self-Improving Coding Agents Build

Authors: Jason Liang, Dylan Waldner, Risto Miikkulainen

Organizations: Cognizant AI Lab

Abstract

Self-improving agents are typically optimized for the results they produce, with less attention to how they produce them. Their instructions give designers limited ways to shape how they work, especially when the task is open-ended. This paper studies whether a short value statement in an agent's persistent instruction file changes not only how well the agent performs but also what it builds. Four higher-order value types in Schwartz's theory of basic human values were evaluated: openness to change, conservation, self-enhancement, and self-transcendence. Across diverse coding tasks, the values were held fixed within each run over multiple iterations of self-improvement. Three findings emerged: (1) Values matter for performance across a diverse set of tasks. The openness values increase performance on held-out data, whereas the opposite conservation values result in scores below those of an agent given no values. (2) Values change what agents build, producing solution algorithms that differ in size, complexity and approach. (3) Human oversight is still needed for designing values. Allowing the agent to revise its own values narrows the differences between sets of values, and values distilled from the AI literature provide no detectable gain over having no values. Properly designed values can thus influence what a self-improving coding agent builds and, where the task permits, how well it performs.

Figures & tables

Appendix figures & tables40 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Evaluation-Free Recursive Self-Improvement for Coding Agents

    Nov 16, 2026Zhe Ren, Guowei Rong, Yimeng Chen +5AI Coding AgentsSelf-Improving Agents

  2. Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

    Nov 5, 2026Wenbo Huang, Jianxin Bi, Shunyu Yang +10Self-Improving AgentsBenchmark Contamination