Tag
AutoMem is a text-gradient recursive self-improvement framework for automated memory architecture search in LLM agents, which discovers task-adaptive architectures that outperform human-designed baselines with improved accuracy and efficiency.
This paper presents a longitudinal evaluation instrument for agent memory that avoids label-error and contamination by generating facts before text, and demonstrates that short-horizon benchmarks can mis-rank memory architectures compared to long-horizon performance. It also releases the Veracium open-source library for agent memory evaluation.
The article explores whether in agentic systems the causal chain of the process is as valuable as the outcome, and questions if memory architectures should store causal threads instead of just raw outputs.
A technical analysis comparing memory designs in RNNs, Transformers, and SSMs, arguing that the key question is where to store sequence state rather than which architecture is better. Discusses trade-offs between compressed hidden states, growing KV caches, and synaptic-like memory in model connectivity.
This paper introduces EnterpriseMem-Bench, a multi-turn Text-to-SQL benchmark, and evaluates five frontier models across memory architectures, finding that stateless models collapse by the third turn and that working memory yields the largest gains.