Tag
This paper proposes TamGraph, a target-aware memory graph method that dynamically selects relevant historical conversations using an entropy-guided mechanism to enhance LLM performance in conversational stance detection tasks.
This paper introduces DREAM, a structured memory framework for LLM-based role-playing agents that uses an Event-aware Memory Graph to maintain temporal and causal coherence, and proposes the TCM benchmark for evaluation.
UML (Universal Memory Layer) is an open-source shared memory graph for Claude, ChatGPT, and other AI agents, letting users save and recall structured memory across tools via MCP with a visual dashboard and API.
MOSAIC is a structured, conflict-aware long-term memory framework for LLM agents that uses entity-typed graph storage, hash-accelerated retrieval, and active conflict detection to achieve high accuracy and efficiency on long-conversation QA and factual conflict detection tasks.
Hermes Agent v0.18.0 'Judgement Release' introduces major workflow upgrades for AI agents, including first-class Mixture-of-Agents (MoA) support, skill learning, visible memory, self-verification, and parallel execution, moving from demo to serious tool.
The author describes a problem where an LLM agent's memory graph gets corrupted by incorrect edges, and proposes using a declared ontology to validate writes and traversals. A test on 120 deliberately broken traversals caught all errors.
A developer reconsiders agent memory as more than storage, proposing a living graph with roles and activation fields to give past information appropriate authority and context.