Pith. sign in

REVIEW 10 cited by

SCM: Enhancing Large Language Model with Self-Controlled Memory Framework

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2304.13343 v4 pith:CWWXZ3TM submitted 2023-04-26 cs.CL

Bing Wang , Xinnian Liang , Jian Yang , Hui Huang , Shuangzhi Wu , Peihao Wu , Lu Lu , Zejun Ma
show 1 more author
Zhoujun Li
This is my paper · ORCID
classification cs.CL
keywords memoryframeworkllmslong-termmemoriesagentdatasetdialogues
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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)

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents

    cs.CR 2026-07 conditional novelty 7.5 of 10

    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.

  2. Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

    cs.LG 2025-12 conditional novelty 6.0 of 10

    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.

  3. Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs

    cs.AI 2026-07 conditional novelty 5.0 of 10

    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.

  4. Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A learnable memory cycle with adaptive retrieval, merging, and storage, trained online, improves LLM agent accuracy on HotpotQA and MemDaily for most backbones.

  5. Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents

    cs.CL 2025-07 conditional novelty 5.0 of 10

    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.

  6. MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents

    cs.CL 2025-06 conditional novelty 5.0 of 10

    MemBench introduces a multi-scenario, multi-level memory benchmark for LLM agents, evaluating factual and reflective memory across participation and observation settings.

  7. Memory OS of AI Agent

    cs.AI 2025-05 conditional novelty 5.0 of 10

    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.

  8. Can Past Experience Accelerate LLM Reasoning?

    cs.LG 2025-05 conditional novelty 5.0 of 10

    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.

  9. MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models

    cs.CL 2025-05 conditional novelty 5.0 of 10

    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.

  10. Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents

    cs.AI 2025-02 conditional novelty 5.0 of 10

    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.

Pith tools