mlsanityData to 7 Oct 2026

MARS: Memory-Enhanced Agents with Reflective Self-improvement

arXiv 2503.19271 ↗First posted 25 Mar 2025cs.CL cs.CVcited by 2

On the map: LLM agents and tool use → Agent memory systems

also in 1 more
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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

25 of 45 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  6. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  7. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  8. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  9. 2019Compressive Transformers for Long-Range Sequence Modellingcited by 699
  10. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  11. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 123
  12. 2023LongCoder: A Long-Range Pre-trained Language Model for Code Completioncited by 110
13 more
  1. 2024Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Surveycited by 82
  2. 2024WcDT: World-centric Diffusion Transformer for Traffic Scene Generationcited by 31
  3. 2025Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversioncited by 28
  4. 2024CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Modelscited by 26
  5. 2024Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Modelscited by 14
  6. 2024DDPM-MoCo: Advancing Industrial Surface Defect Generation and Detection with Generative and Contrastive Learningcited by 10
  7. 2025TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancementcited by 9
  8. 2023SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistencycited by 8
  9. 2025PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Netcited by 8
  10. 2024GAgent: An Adaptive Rigid-Soft Gripping Agent with Vision Language Models for Complex Lighting Environmentscited by 6
  11. 2024Neural network based model predictive control of voltage for a polymer electrolyte fuel cell system with constraintscited by 5
  12. 2025A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Modelscited by 5
  13. 2024Voltage Regulation in Polymer Electrolyte Fuel Cell Systems Using Gaussian Process Model Predictive Controlcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2025ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agentscited by 7

Similar, not cited

Close in wording, no citation either way

  1. 2024Self-evolving Agents with reflective and memory-augmented abilities
  2. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  3. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  4. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  5. 2026AdMem: Advanced Memory for Task-solving Agents
  6. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  7. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
  8. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory