MemAgent: Learning to Manage Heterogeneous Memory Providers for LLM Agents
Current agents remain largely stateless across tasks, limiting their ability to continually improve from prior interactions and making memory essential for long-horizon agentic behavior. Existing memory methods seek to reuse past experience, but most rely on a single memory representation (e.g., trajectories, reflectio...
Yong-Xian Wei, Yi-Lin Zhao, Run-Xi Cheng et al.
· 0 citations