TechniqueRLHF / Alignment1 recent entries29 May 2026Beyond Recall: Behavioral Specification as an Interpretive Layer for AI PersonalizationarXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f
TechniqueRAG2 recent entries15 Apr 2026Memory as Metabolism: A Design for Companion Knowledge SystemsarXiv:2604.12034v1 Announce Type: new Abstract: Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory archi
TechniqueAgents8 recent entries30 Jun 2026Zep: Unified agent memory across MCP clientsZep says its MCP server shares persistent user memory across agents with SSO, retention policy and Zep Cloud or customer VPC deployment.→14 Aug 2026FluctlightDB: A Memory Model of Data for AI AgentsarXiv:2608.12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which ve→17 Aug 2026LettaLetta's agent-memory SDK supports persistent agent memory across managed cloud, self-hosted App Server or local deployment, according to Letta.→19 Aug 2026ZepZep offers a knowledge graph for persistent user memory and shared organisational context through MCP, according to Zep.→1 Sept 2026post-graph-rag: A PostgreSQL-Native Bi-Temporal Graph RAG Engine with Temporal Grounding at SynthesisarXiv:2608.24921v2 Announce Type: replace Abstract: Graph RAG connects facts no single passage states, but implementations pay three times: in infrastructure, keeping vector store, graph database and →14 Sept 2026Best Knowledge Engine Platforms in 2026This guide identifies six leading knowledge‑engine platforms in 2026—Pinecone Nexus, Databricks Genie, Snowflake Cortex, Microsoft IQ, Palantir Foundry, and Glean—that each transform heterogeneous dat→16 Sept 2026Mem0Mem0 provides persistent user memory and agent memory; its vendor describes fact extraction, contradiction handling and relevant recall.→7 Oct 2026Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI AgentsarXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester
TechniqueFine-tuning1 recent entries30 Jul 2026InferScale: GPU-Native KV Injection for Personalized LLM ServingarXiv:2607.27090v1 Announce Type: cross Abstract: Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histori
TechniqueSafety2 recent entries15 Apr 2026Memory as Metabolism: A Design for Companion Knowledge SystemsarXiv:2604.12034v1 Announce Type: new Abstract: Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory archi→7 Oct 2026Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI AgentsarXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester