# Memory-Driven Self-Improvement for Decision Making with Large Language Models

arXiv: https://arxiv.org/abs/2509.26340 · HTML: https://mlsanity.com/paper/2509.26340/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [Maximum a Posteriori Policy Optimisation](https://mlsanity.com/paper/1806.06920/) (2018)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [LLM Critics Help Catch LLM Bugs](https://mlsanity.com/paper/2407.00215/) (2024)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)
- [Motif: Intrinsic Motivation from Artificial Intelligence Feedback](https://mlsanity.com/paper/2310.00166/) (2023)
- [Large Language Models for Robotics: Opportunities, Challenges, and Perspectives](https://mlsanity.com/paper/2401.04334/) (2024)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering](https://mlsanity.com/paper/2404.04302/) (2024)
- [BioRAG: A RAG-LLM Framework for Biological Question Reasoning](https://mlsanity.com/paper/2408.01107/) (2024)
- [Efficient Reinforcement Learning with Large Language Model Priors](https://mlsanity.com/paper/2410.07927/) (2024)
- [Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics](https://mlsanity.com/paper/2211.02231/) (2022)

## Abstract (arXiv)

Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet general knowledge is often insufficient for specific decision-making tasks with limited task-related data, making it challenging to efficiently adapt LLMs to specific SDM tasks. To address this challenge, we propose a memory-driven self-improvement framework that combines LLM general prior knowledge with a compact memory of domain-specific experiences. Memory retains past interactions and associated Q-values, thereby capturing decision-relevant knowledge that facilitates accurate value estimation and informs the LLM prior refinement. The refined LLM prior, in turn, generates higher-reward trajectories that further enrich memory, forming a natural self-improvement framework where memory and LLM prior mutually reinforce each other. Experiments show that our memory-driven approach significantly outperforms both traditional RL and LLM-based baselines, e.g., improving performance by over 40% on in-distribution tasks and over 75% when generalized to unseen tasks in ALFWorld.