AI RESEARCH
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents
arXiv CS.LG
•
ArXi:2601.14287v2 Announce Type: replace External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive memory construction (e.g., structuring data into graphs) followed by naive retrieval-augmented generation.