Survey Redefines 'Self-Improving Agents': Fast Exploration, Slow Consolidation

新智元 · wechat · 2026-08-10

A joint survey from Jilin University, KAUST, and other institutions redefines "Self-Improving Agents," mapping model training, memory evolution, tool creation, and architecture search into a unified framework, alongside 312 related works.

The Boundary: True self-improvement occurs only when a system persistently modifies its foundation model parameters or scaffolding (Prompts, Memory, Tools) based on execution trajectories, altering the starting point for future tasks. One-off reflections don't count.

Two Core Paths:

Design Principle: Mature systems should adopt a dual-timescale approach: using scaffolding for fast, reversible exploration, and distilling proven experiences into model weights for slow consolidation. As agents gain self-modification capabilities, robust safety mechanisms like layered gating are crucial to prevent persistent vulnerabilities.

Original post →

More from coding & agent

coding & agent channel →