User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
Beyond the context window: A cost-performance analysis of fact-based memory vs. long-context llms for persistent agents
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
MemDelta shows agent memory evaluations are confounded by LLM family and embedding model, with RAG often matching full context and self-memory underperforming basic retrieval.
ProjectMem implements a local event-sourced memory and judgment layer for AI coding agents that logs typed events, projects them to MCP summaries, and applies deterministic pre-action gates to avoid known failures.
An agentic harness letting the LLM self-manage flat text-file storage via tool calls outperforms eight prior memory systems on cross-scenario generality across QA, chat, trajectory, stress-test, and long-horizon tasks.
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
A four-query experiment demonstrates 84.6% token savings through knowledge compounding in self-evolving wikis compared to standard RAG, by amortizing ingestion costs and reusing synthesized knowledge over time.
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
citing papers explorer
-
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
-
MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation
MemDelta shows agent memory evaluations are confounded by LLM family and embedding model, with RAG often matching full context and self-memory underperforming basic retrieval.
-
PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
ProjectMem implements a local event-sourced memory and judgment layer for AI coding agents that logs typed events, projects them to MCP summaries, and applies deterministic pre-action gates to avoid known failures.
-
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
An agentic harness letting the LLM self-manage flat text-file storage via tool calls outperforms eight prior memory systems on cross-scenario generality across QA, chat, trajectory, stress-test, and long-horizon tasks.
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
-
Knowledge Compounding: An Empirical Economic Analysis of Self-Evolving Knowledge Wikis under the Agentic ROI Framework
A four-query experiment demonstrates 84.6% token savings through knowledge compounding in self-evolving wikis compared to standard RAG, by amortizing ingestion costs and reusing synthesized knowledge over time.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.