Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory
cs.AI, cs.CL, cs.IR
Submitted: 2025-12-23
Updated: 2026-11-14
Code: https://github.com/tao-hpu/cog-canvas
Terminology
Sources
- Longformer: The Long-Document Transformer
- Extending Context Window of Large Language Models via Positional Interpolation
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Generating Long Sequences with Sparse Transformers
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- LightRAG: Simple and Fast Retrieval-Augmented Generation
- Atlas: Few-shot Learning with Retrieval Augmented Language Models
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Recursively Summarizing Books with Human Feedback
- A-MEM: Agentic Memory for LLM Agents
- On the Structural Memory of LLM Agents
- A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents