Research

Paper

AI LLM February 20, 2026

Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning

Authors

Narjes Nourzad, Carlee Joe-Wong

Abstract

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for subgoal discovery and trajectory guidance. While LLMs can support exploration, frequent reliance on LLM calls raises concerns about scalability and reliability. We address these challenges by constructing a memory graph that encodes subgoals and trajectories from both LLM guidance and the agent's own successful rollouts. From this graph, we derive a utility function that evaluates how closely the agent's trajectories align with prior successful strategies. This utility shapes the advantage function, providing the critic with additional guidance without altering the reward. Our method relies primarily on offline input and only occasional online queries, avoiding dependence on continuous LLM supervision. Preliminary experiments in benchmark environments show improved sample efficiency and faster early learning compared to baseline RL methods, with final returns comparable to methods that require frequent LLM interaction.

Metadata

arXiv ID: 2602.17931
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-20
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17931v1</id>\n    <title>Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning</title>\n    <updated>2026-02-20T01:44:35Z</updated>\n    <link href='https://arxiv.org/abs/2602.17931v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17931v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for subgoal discovery and trajectory guidance. While LLMs can support exploration, frequent reliance on LLM calls raises concerns about scalability and reliability. We address these challenges by constructing a memory graph that encodes subgoals and trajectories from both LLM guidance and the agent's own successful rollouts. From this graph, we derive a utility function that evaluates how closely the agent's trajectories align with prior successful strategies. This utility shapes the advantage function, providing the critic with additional guidance without altering the reward. Our method relies primarily on offline input and only occasional online queries, avoiding dependence on continuous LLM supervision. Preliminary experiments in benchmark environments show improved sample efficiency and faster early learning compared to baseline RL methods, with final returns comparable to methods that require frequent LLM interaction.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-20T01:44:35Z</published>\n    <arxiv:comment>Association for the Advancement of Artificial Intelligence (AAAI)</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Narjes Nourzad</name>\n    </author>\n    <author>\n      <name>Carlee Joe-Wong</name>\n    </author>\n  </entry>"
}