MARS: Memory-Enhanced Agents with Reflective Self-improvement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913785681281024 |
|---|---|
| author | Liang, Xuechen Tao, Meiling Xia, Yinghui Wang, Jianhui Li, Kun Wang, Yijin Yang, Jingsong Shi, Tianyu Wang, Yuantao Zhang, Miao Wang, Xueqian |
| author_facet | Liang, Xuechen Tao, Meiling Xia, Yinghui Wang, Jianhui Li, Kun Wang, Yijin Yang, Jingsong Shi, Tianyu Wang, Yuantao Zhang, Miao Wang, Xueqian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19271 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MARS: Memory-Enhanced Agents with Reflective Self-improvement Liang, Xuechen Tao, Meiling Xia, Yinghui Wang, Jianhui Li, Kun Wang, Yijin Yang, Jingsong Shi, Tianyu Wang, Yuantao Zhang, Miao Wang, Xueqian Computation and Language Computer Vision and Pattern Recognition 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. |
| title | MARS: Memory-Enhanced Agents with Reflective Self-improvement |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.19271 |