REVIEW 15 cited by
SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
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
Signed reviews
read the original abstract
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information. Our SCM framework comprises three key components: an LLM-based agent serving as the backbone of the framework, a memory stream storing agent memories, and a memory controller updating memories and determining when and how to utilize memories from memory stream. Additionally, the proposed SCM is able to process ultra-long texts without any modification or fine-tuning, which can integrate with any instruction following LLMs in a plug-and-play paradigm. Furthermore, we annotate a dataset to evaluate the effectiveness of SCM for handling lengthy inputs. The annotated dataset covers three tasks: long-term dialogues, book summarization, and meeting summarization. Experimental results demonstrate that our method achieves better retrieval recall and generates more informative responses compared to competitive baselines in long-term dialogues. (https://github.com/wbbeyourself/SCM4LLMs)
Forward citations
Cited by 15 Pith papers
-
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents
Malicious tools can systematically extract isolated LLM-agent long-term memory via persistence, pure-anchor retrieval steering, and reactivation payloads, reaching 80% extraction with unlimited triggers and 47% with 20.
-
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
An LLM agent that builds a tool-transition graph with state summaries from past experience improves tool selection and RL exploration by large margins on multi-turn benchmarks.
-
CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents
CAIM, a cognitive-AI-inspired memory framework with ontology-based tagging and relevance filtering, improves retrieval and response correctness for LLM assistants on the Generated Virtual Dataset compared with MemoryB...
-
Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
Graph-based action memory with dual-stream TD learning improves best-of-N inference scaling for LLM agents, reporting +20.81% success / +6.17% progress over vanilla baselines.
-
Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
A learnable memory cycle with adaptive retrieval, merging, and storage, trained online, improves LLM agent accuracy on HotpotQA and MemDaily for most backbones.
-
Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
H-MEM organizes LLM agent memory into a four-level semantic hierarchy with pointer-based coarse-to-fine retrieval, improving average LoCoMo QA scores over five baselines while cutting retrieval cost.
-
MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
MemBench introduces a multi-scenario, multi-level memory benchmark for LLM agents, evaluating factual and reflective memory across participation and observation settings.
-
Memory OS of AI Agent
A hierarchical short/mid/long-term memory system with OS-style segmented paging and heat-based eviction improves LLM response accuracy on long-conversation benchmarks.
-
Can Past Experience Accelerate LLM Reasoning?
LLMs can cut reasoning compute by up to 56% on similar questions when memory of past correct solutions is combined with adaptive early stopping, though the benchmark is small and synthetic.
-
MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models
MiniLongBench, a 237-sample compression of LongBench, is claimed to reproduce model rankings with a 0.97 Spearman correlation at 4.5% of the evaluation cost.
-
MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents
MemEngine is a modular library that standardizes and reimplements nine memory models from LLM-agent research under a unified function-operation-model hierarchy.
-
Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
The authors propose episodic memory, with five defining properties, as the unifying framework needed for LLM agents to learn and remember over long time horizons.
-
CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding
A category-bounded LLM memory system for in-car voice assistants achieves .78 to .95 F1 for preference extraction, 92 to 95 percent reduction of redundant and contradictory stored preferences, and .87 retrieval accura...
-
Addressing the sustainable AI trilemma: a case study on LLM agents and RAG
LLM-dependent memory operations in agents and RAG consume orders of magnitude more energy than vector methods, and resource-constrained hardware pays higher energy for lower quality.
-
Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset
A retrieve-summarize-extract pipeline with simple table-to-text serialization improves LLM extraction from hybrid long documents, and a new financial KPI dataset (FINE) is introduced to support evaluation.
Discussion (0). Continue with ORCID to comment.