Harel Lidar

Article summary · Oct 2026

Continual Learning for Agents

Mostly someone else’s words, from Jiaxin Zhang: Continual Learning for Next-Generation Agents. I keep it as reading, not as my own writing. Read the original ↗

TL;DR

What is CL - The stack, and what each layer gives

The author claims that “learning” can happen in different levels with them producing a cost gradient. The higher the level, the more powerful it is but it is also more dangerous and more demanding of evidence. The levels differ in what their scope is, where their updates happen and in their characteristic failures.

The deployment loop - translating experience to durable results

Critical Loop Requirements

Translating Classic CL to Agentic CL

Current status of the Field

The Rungs of CL

Evaluating CL

Failure Modes

Common pitfalls for these systems aren’t loud failures, they instead degrade through time in a way that makes it looks like success early on. Make sure to avoid:

Takeaways

Plausible Research Agenda