-
Notifications
You must be signed in to change notification settings - Fork 20
Description
Hi authors,
Thank you for your excellent work on "Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks." The concept of an experience-driven, self-evolving agent is a fascinating and significant step forward for solving long-horizon problems.
I'm writing to gently suggest a relevant paper that could be a good addition to your related work section: "A-Mem: Agentic Memory for LLM Agents", which was accepted at NeurIPS 2025.
Our paper proposes a novel framework for agentic memory, which is a core component for any agent that needs to learn from past experiences. Since your work focuses on an "experience-driven" agent, we believe the memory architecture discussed in "A-Mem" is highly relevant and could provide valuable context for readers.
For your convenience, here is the citation information:
Title: A-Mem: Agentic Memory for LLM Agents
Conference: NeurIPS 2025
Link to paper: https://arxiv.org/abs/2502.12110
Thank you for your consideration and for your contribution to the community!