#llm-memory

0 stories this week · 2 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

3 stories, newest first · one card per story

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue

TrackMem uses per-speaker graph memory to track revised figures and shifting stances across sessions in financial dialogues where facts change over time.

llm-memory long-horizon-dialogue

Hugging Face daily papers21d ago

Naive RAG beats complex agentic memory on conversation benchmarks

Raw-RAG ranked first in six of seven settings, ahead of the best agentic system by 0.13 to 5.53 points.

rag agentic-memory

arXiv cs.AI / cs.LG / cs.CLSep 9, 2026

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

Fortunate Recall introduces ontology-based lifecycle policies for LLM memory, cutting confabulation roughly in half (e.g., 45.1% to 22.4%) versus Mem0.

benchmarks confabulation

Stories tagged #llm-memory

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue

Naive RAG beats complex agentic memory on conversation benchmarks

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs