@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.

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.

Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

arXiv cs.AI

This paper introduces HiGram, an evolving hierarchical graph memory framework for LLM agents that features path-level localization and coordinated rewriting to improve retrieval efficiency and answer quality in long-term reasoning tasks.

From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents

arXiv cs.AI

This paper studies how memory architecture affects language emergence in LLM agents playing a Lewis signaling game, finding that persistent private notebook memory outperforms stateless agents and prevents high-capacity collapse.