Do LLM Agents Still Need to Be Told How to Self-Improve?
Shobhita Sundaram, Cansu Sancaktar, Phillip Isola
Do LLM Agents Still Need to Be Told How to Self-Improve?: 5 upvotes on Hugging Face Daily Papers, #22 of 39 papers on 2026-11-18. Day-by-day upvote history.
Upvotes over time
It had 5 upvotes by its first day, 5 upvotes by the next day, 5 upvotes by day 3, 5 upvotes by day 7, and has 5 now. It ranked #75 of 146 papers in its week and #323 of 520 in its month. Its code repository has 3 GitHub stars.
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 experiment without an externally imposed loop or access to real-world data. We find that sufficiently capable models do self-improve under these conditions, demonstrating strategies that align with classic cognitive frameworks for self-regulated learning and constructs from machine learning literature on self-generated curricula. Furthermore, we study the extent to which the learned text artifacts transfer to external benchmarks, observing improvement across different game horizons, mechanics, and 3D navigation.
Paper page on Hugging Face · arXiv
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.