# Do LLM Agents Still Need to Be Told How to Self-Improve?

Source: [arXiv](https://arxiv.org/abs/2611.23219v1)  
Feed7 permalink: https://feed7.dev/p/do-llm-agents-still-need-to-be-told-how-to-self-improve-db243fa757  
Published: 2026-11-17T00:00:00.000Z  
Trust: Needs Review (needs_review)

## Why Included

Let agents refine bounded task notes and procedures, but evaluate whether those artifacts transfer to held-out tasks before keeping them.

## Source Summary

A gameplay study finds capable agents can devise their own learning loops from basic tools and a goal, then transfer some learned text artifacts to other tasks. It tests an early form of agent-directed improvement.

## Practical Implication

For coding agents, this suggests testing whether they can improve task-specific notes or procedures when given clear goals, tools, and bounded resources. Measure transfer to held-out tasks rather than assuming a self-written playbook will generalize.

## Agent-Ready Context

A frozen agent received a compute budget, experience-gathering tools, editable text documents, and a general self-improvement goal. It experimented without a prescribed learning loop or real-world data, and some learned artifacts transferred across game horizons, mechanics, and 3D navigation.

For coding agents, this suggests testing whether they can improve task-specific notes or procedures when given clear goals, tools, and bounded resources. Measure transfer to held-out tasks rather than assuming a self-written playbook will generalize.

The evidence comes from gameplay, and the material gives no quantitative effect sizes or cost comparisons. It does not establish that the approach works for software engineering tasks.

## Context Map

- Layer: agent
- Domains: coding, research
- Topics: harness-engineering, agent-memory, agent-evals

## Uncertainty

- Automatically selected from source material; feed7 has not independently tested the claim.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
