@neural_avb: Here's the latest paper on Graph Memory on LLM agents

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

Hugging Face Daily Papers

MRAgent introduces a novel graph-based memory framework that dynamically reconstructs memory during reasoning, achieving up to 23% improvement on long-horizon benchmarks while reducing computational costs.

Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents

arXiv cs.AI

This paper evaluates a graph-based memory framework for long-term LLM agents, finding that it does not outperform flat vector retrieval on recall metrics, but a selective forgetting module effectively reduces storage with minimal performance loss.

ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents

arXiv cs.CL

ExpGraph is a model-agnostic framework that enables LLM agents to reuse past experiences via a self-evolving graph of skills and failures, improving task performance by 12–21% without retraining the executor.

@neural_avb: There are two to three completely different schools of thoughts for building memory systems into LLMs. When it comes to…

X AI KOLs Timeline

Discussion of different schools of thought for building memory systems in LLMs, with a focus on graph memory and its potential for human creativity and inductive bias.

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents

arXiv cs.CL

The paper introduces REALM, a framework for long-term memory in LLM agents that uses retrieval-driven reconsolidation to autonomously organize memories into a cognitive graph, achieving improved performance on long-term memory benchmarks.