LLM Digest

Story

arxiv_llm_reliability · Nov 12, 2026 · paper

Source brief

We Are What We Remember: Mental-State-Driven Memory for Long-Term Character Dialogue

arxiv.orgNov 12, 2026
original source linked

In brief

Shared history in human dialogue is not merely a repository of facts, but the foundation of evolving relationships and mutual understanding. However, mainstream conversational memory systems rely on passive semantic s...

Feed lens

agenteval

Read the original at arxiv.org →Open in live feed Read that day’s brief

We Are What We Remember: Mental-State-Driven Memory for Long-Term Character Dialogue

Earlier in this thread 4 items

FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue

What Is This Memory Useful For? Measuring Task-Conditioned Utility in Long-Term Agent Memory

A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory

ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents