Pith. sign in

REVIEW 11 cited by

Cognitive Memory in Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.02441 v2 pith:5RRD27MG submitted 2025-04-03 cs.CL cs.AI

Cognitive Memory in Large Language Models

classification cs.CL cs.AI
keywords memorymechanismscompressionmethodsapproachesefficiencylanguagelarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL queries, semantic search). The KV cache-based memory section discusses selection methods (regularity-based summarization, score-based approaches, special token embeddings) and compression techniques (low-rank compression, KV merging, multimodal compression), along with management strategies like offloading and shared attention mechanisms. Parameter-based memory methods (LoRA, TTT, MoE) transform memories into model parameters to enhance efficiency, while hidden-state-based memory approaches (chunk mechanisms, recurrent transformers, Mamba model) improve long-text processing by combining RNN hidden states with current methods. Overall, the paper offers a comprehensive analysis of LLM memory mechanisms, highlighting their significance and future research directions.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

    cs.AI 2026-04 unverdicted novelty 7.0

    SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.

  2. MIRIX: Multi-Agent Memory System for LLM-Based Agents

    cs.CL 2025-07 unverdicted novelty 7.0

    MIRIX introduces a modular multi-agent architecture with Core, Episodic, Semantic, Procedural, Resource, and Knowledge Vault memories that outperforms RAG baselines by 35% on ScreenshotVQA and reaches 85.4% on LOCOMO.

  3. ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

    cs.LG 2026-06 unverdicted novelty 6.0

    ECHO is a selective turn-memory framework for agentic RL that compresses turns into indexed records, selects them for bounded contexts, and uses source indices to assign outcome credit to supporting evidence, reaching...

  4. ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

    cs.LG 2026-06 conditional novelty 6.0

    ECHO stores each completed agent turn as a source-indexed memory, selects memories for bounded context, and uses those same indices to route positive RL credit, improving long-horizon tool-use accuracy.

  5. ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

    cs.LG 2026-06 conditional novelty 6.0

    ECHO's source-indexed memory records let context reconstruction and RL credit assignment share one trace, reaching 43.4% on BrowseComp-Plus vs 28.9% (GRPO) and 36.1% (SUPO).

  6. ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

    cs.LG 2026-06 conditional novelty 6.0

    Source-indexed selective turn memory plus provenance-guided credit assignment raises BrowseComp-Plus accuracy to 43.4% over GRPO and SUPO while cutting turn proliferation.

  7. Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery

    cs.LG 2026-05 unverdicted novelty 6.0

    Empirical evaluation of eight memory condensation strategies on 480 DiscoveryBench tasks finds no significant impact on hypothesis quality but domain-dependent differences in token efficiency.

  8. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

    cs.CV 2026-01 unverdicted novelty 6.0

    HERMES organizes the KV cache into a hierarchical memory to enable real-time streaming video understanding in MLLMs, achieving 10x faster TTFT and up to 11.4% accuracy gains on streaming benchmarks with 68% fewer tokens.

  9. MemOS: A Memory OS for AI System

    cs.CL 2025-07 unverdicted novelty 5.0

    MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.

  10. A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

    cs.AI 2025-07 accept novelty 4.0

    The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.

  11. Context Recycling for Long-Horizon LLM Inference

    cs.CL 2026-05 unverdicted novelty 3.0

    ContextForge recycles context in long-horizon LLM tasks via query generation, memory retrieval, and synthesis, yielding reduced token use and improved consistency on a 15-turn healthcare benchmark while preserving accuracy.