liveBook · Manning

Memory layer

As explained in Self-Improving Agents

The agent infrastructure layer that retains information learned across tasks, including entries, trajectories, values, and records of successful approaches.

The memory layer retains what an agent learns across tasks. Its artifacts can be edited directly so useful lessons persist for later tasks, without changing the model itself. section 1.3.2 section 1.5

Memory artifacts include:

  • Stored entries and recorded trajectories. section 1.3.2
  • Learned values and records of tools or approaches that worked. section 1.3.2
  • Skill files, which are text artifacts that memory can also store and retrieve. section 1.3.2

Improving memory means adding useful entries, correcting misleading ones, consolidating redundant ones, or strengthening those that have paid off. These edits put lessons within reach on subsequent tasks. section 1.3.2

Figure 1.8 The harness artifact layers of self-improvement. The frozen model (LLM) serves as the unchanging substrate below. The four artifact layers stacked on it are shared infrastructure, inherited by every instance of the agent. Layer zero is the toolkit, the engineering work that measures, searches, and applies, reused at every layer.

The diagram situates memory among the harness artifact layers, beneath the frozen model and alongside the other shared infrastructure. section 1.3.2 section 1.5

How Self-Improving Agents covers it

How deep it goes
Defines memory artifacts and direct editing operations, but does not detail storage or retrieval mechanics.
Examples
Uses stored entries, trajectories, learned values, and records of successful tools or approaches as examples.
What you can do after
Operate it by adding useful entries, correcting misleading ones, consolidating redundancies, or strengthening successful records.
How it connects
Connects memory to skill files, prompts, metacognitive scaffolds, the agent harness, and the act-signal-search-apply loop.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Self-Improving Agents. The section links point to the parts of the book it draws on.