# MARS: Memory-Enhanced Agents with Reflective Self-improvement

arXiv: https://arxiv.org/abs/2503.19271 · HTML: https://mlsanity.com/paper/2503.19271/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing](https://mlsanity.com/paper/2404.12253/) (2024)
- [LongCoder: A Long-Range Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2306.14893/) (2023)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [WcDT: World-centric Diffusion Transformer for Traffic Scene Generation](https://mlsanity.com/paper/2404.02082/) (2024)
- [Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion](https://mlsanity.com/paper/2501.04606/) (2025)
- [CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models](https://mlsanity.com/paper/2404.01663/) (2024)
- [Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Models](https://mlsanity.com/paper/2405.04135/) (2024)
- [DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learning](https://mlsanity.com/paper/2407.03332/) (2024)
- [TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2503.08168/) (2025)
- [SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistency](https://mlsanity.com/paper/2305.08053/) (2023)
- [PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Net](https://mlsanity.com/paper/2503.08276/) (2025)
- [GAgent: An Adaptive Rigid-Soft Gripping Agent with Vision Language Models for Complex Lighting Environments](https://mlsanity.com/paper/2403.10850/) (2024)
- [Neural network based model predictive control of voltage for a polymer electrolyte fuel cell system with constraints](https://mlsanity.com/paper/2406.16871/) (2024)
- [A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models](https://mlsanity.com/paper/2503.08199/) (2025)
- [Voltage Regulation in Polymer Electrolyte Fuel Cell Systems Using Gaussian Process Model Predictive Control](https://mlsanity.com/paper/2403.16170/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents](https://mlsanity.com/paper/2509.25299/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making, lack of long-term memory, and limited context windows in dynamic environments. To address these issues, this paper proposes an innovative framework Memory-Enhanced Agents with Reflective Self-improvement. The MARS framework comprises three agents: the User, the Assistant, and the Checker. By integrating iterative feedback, reflective mechanisms, and a memory optimization mechanism based on the Ebbinghaus forgetting curve, it significantly enhances the agents capabilities in handling multi-tasking and long-span information.