TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue
Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumption: figures are revised, stances shift without being restated, rules stated once govern later questions, and a single company is discussed under several analytical…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
