About this paper
Capable frozen LLM agents can autonomously construct context-based self-learning algorithms from basic resources and a general goal, yielding text artifacts that transfer to new game and 3D navigation tasks.
LLM agents increasingly drive their own learning. Self-improvement methods delegate various components of model optimization to the models themselves. As models become more capable, this motivates a basic question: do these increasingly capable models still need us to specify how they should self-improve? In this paper we study an autonomous paradigm in which, given basic primitives, resources, and a general goal for self-improvement, agents construct their own self-learning algorithm for context-based optimization. Using the setting of gameplay as a testbed, a frozen LLM agent is given a compute budget and tools for collecting experience and updating text documents, and allowed to freely…
LLM agentsself-improvement methodsmodel optimizationautonomous paradigmself-learning algorithmcontext-based optimizationfrozen LLM agentself-generated curriculatransfer to external benchmarks3D navigation
- Upvotes
- 6
- Authors
- 3
- Published
- Nov 17, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Do LLM Agents Still Need to Be Told How to Self-Improve? was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 10 checks on 2 different days. Its best position was #20 of 30, reached on Nov 19, 05:28 UTC. It dropped off the list after Nov 19, 05:28 UTC.