paper-with-me

Papers

MARS: Memory-Enhanced Agents with Reflective Self-improvement

2025-03-25 · Xuechen Liang, Meiling Tao, Yinghui Xia, Jianhui Wang, Kun Li, Yijin Wang, Jingsong Yang, Tianyu Shi, Yuantao Wang, Miao Zhang, Xueqian Wang

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.

📄 PDF Abstract BibTeX arXiv:2503.19271

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement

2026-01-17 · Xinmeng Hou, Peiliang Gong, Bohao Qu, Wuqi Wang 외 arxiv

While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge thi…

MARS: Modular Agent with Reflective Search for Automated AI Research

2026-02-02 · Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam, Rui Meng 외 arxiv

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model…

Self-evolving Agents with reflective and memory-augmented abilities

2024-09-01 · Xuechen Liang, Yangfan He, Yinghui Xia, Xinyuan Song 외

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. In this research, we propose a novel framework b…

Decision Making

ParamMem: Augmenting Language Agents with Parametric Reflective Memory

2026-02-26 · Tianjun Yao, Yongqiang Chen, Yujia Zheng, Pan Li 외 arxiv

Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various ap…

Multi-hop Question AnsweringMathematical ReasoningCode Generation

Honest Lying: Understanding Memory Confabulation in Reflexive Agents

2026-05-28 · Prakhar Dixit, Sadia Kamal, Tim Oates arxiv

Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures. We show that this assumption can fail systematically: across ALFWorld and H…