AICLLGJul 14

Self-Improvements in Modern Agentic Systems: A Survey

arXiv:2607.1310449.0h-index: 17Has Code
Predicted impact top 1% in AI · last 90 daysOriginality Synthesis-oriented
AI Analysis

For researchers and practitioners building autonomous agents, this survey provides a systematic framework to understand and compare self-improvement mechanisms, though it is a review rather than a novel contribution.

This survey frames modern self-improving agents as adaptive systems that convert experience into capability gains, formalizing self-improvement as a self-induced update operator. It organizes prior work by update target and driving signals, reviews applications, and discusses evaluation and open problems.

Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input. This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern agent as a configuration coupling a foundation model with an operational scaffold of prompts, memory, tools, and control logic. Within this framework, self-improvement is formalized as a self-induced update operator that obtains and commits updates to model parameters or scaffold components. We organize prior work by update target and by the signals that drive change, then review applications and discuss evaluation, before closing with open problems and future directions. For convenience, we track technical updates on https://github.com/selfimproving-agent/awesome-Self-Improving-Agents.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes