trends.barnas.net

method · first seen 7 Oct 2026

LLM-guided reinforcement learning

Using a large language model during training to provide guidance or reward signals for a reinforcement learning agent that is discarded at deployment.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

proximal policy optimizationreward shaping