Papers with memory mechanism
H-MEM: Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents (2026.eacl-long)
Copied to clipboard
| Challenge: | Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents. |
| Approach: | They propose a hierarchical memory architecture that organizes and updates memory in a multi-level fashion based on the degree of semantic abstraction. |
| Outcome: | The proposed model outperforms baseline methods on five task settings from the LoCoMo dataset. |
Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories (2021.emnlp-main)
Copied to clipboard
| Challenge: | Detecting salient events is an essential part of understanding narrative, and is used to aid storyline writing and summarisation. |
| Approach: | They propose an unsupervised method for salience detection derived from Barthes Cardinal Functions and theories of surprise and apply it to longer narrative forms. |
| Outcome: | The proposed method improves performance over a non-knowledgebase and memory augmented language model on longer works. |
Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale (2022.tacl-1)
Copied to clipboard
| Challenge: | a novel class of Transformer language models that combine expressive power, scalability, and strong performance of Transformers and recursive syntactic compositions. |
| Approach: | They introduce Transformer Grammars, a class of Transformer language models that combine expressive power and recursive syntactic compositions. |
| Outcome: | The proposed model outperforms strong baselines on sentence-level language modeling perplexity and syntax-sensitive language evaluation metrics. |
Event Pattern-Instance Graph: A Multi-Round Role Representation Learning Strategy for Document-Level Event Argument Extraction (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing role-based span selection strategies ignore interrelations between events . authors propose a multi-round role representation learning strategy for document-level event argument extraction . |
| Approach: | They propose a pattern-instance graph to capture role semantics embedded in various associations . they also propose re-inventing the role representations learned from previous analyzed documents . |
| Outcome: | The proposed model captures role semantics embedded in various associations . iteratively updates representations of role nodes and edges to enrich their semantic information . the model improves prediction performance in subsequent rounds of span selection . |
Sliding Selector Network with Dynamic Memory for Extractive Summarization of Long Documents (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing summarization models suffer from the length limitation of text encoder, which results in huge loss of summary-relevant contents. |
| Approach: | They propose a sliding selector network with dynamic memory for extractive summarization of long-form documents that employs a window to extract summary sentences segment by segment. |
| Outcome: | The proposed model outperforms state-of-the-art models on two large-scale datasets showing that it is highly efficient and fluent. |
Coarse-to-Fine Grounded Memory for LLM Agent Planning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to enhance LLM with offline experiences or online trajectory analysis focus on single-granularity memory derived from dynamic environmental interactions. |
| Approach: | They propose a framework that grounds coarse-to-fine memories with LLM to enable flexible adaptation to diverse scenarios. |
| Outcome: | Extensive experiments on AlfWorld, Webshop and ScienceWorld show that the proposed framework outperforms baselines and comprehensively optimizes memory-enhanced LLM Agent system. |
Improving Chinese Word Segmentation with Wordhood Memory Networks (2020.acl-main)
Copied to clipboard
| Challenge: | Contextual features are important in Chinese word segmentation (CWS) but it is difficult to integrate wordhood information into existing neural models. |
| Approach: | They propose a neural framework that integrates contextual wordhood information with several popular encoder-decoder combinations for Chinese word segmentation. |
| Outcome: | The proposed framework achieves state-of-the-art performance on five benchmark datasets. |
Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on hallucination detection rely heavily on closed-source LLMs such as GPT-4. |
| Approach: | They propose an LLM-based agent framework called HaluAgent that integrates LLMs, multi-functional toolbox and a memory mechanism for hallucination detection. |
| Outcome: | The proposed framework integrates the LLM, multi-functional toolbox, and can detect hallucinations on Chinese and English datasets. |
Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for storing and retrieving memory are limited by shallow semantic retrieval. |
| Approach: | They propose a memory mechanism that organizes and retrieves past experiences to support decision-making. |
| Outcome: | Experiments on LoCoMo and NarrativeQA show that CompassMem improves retrieval and reasoning performance across multiple backbone models. |
AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation (2025.findings-acl)
Copied to clipboard
Ming Wang, Peidong Wang, Lin Wu, Xiaocui Yang, Daling Wang, Shi Feng, Yuxin Chen, Bixuan Wang, Yifei Zhang
| Challenge: | Existing models of seeker simulations are limited by the cost and ethical concerns of involving real seekers in mental health research. |
| Approach: | They propose an emotional and cognitive dynamic agent system equipped with tertiary memory to enable dynamic control of the simulator's configurations. |
| Outcome: | The proposed system achieves more realistic seeker simulation compared to baselines. |
HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize agent performance by incorporating entire historical action-observation pairs into LLMs are redundant in long-horizon tasks. |
| Approach: | They propose a framework that leverages subgoals as memory chunks to manage working memory of LLM-based agents hierarchically. |
| Outcome: | The proposed framework achieves a twofold increase in success rate and reduces the average number of steps required by 3.8. |
EvoMemKG: An Evolvable Memory Agent for Multi-hop Knowledge Graph Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for integrating knowledge graphs with large language models lack continuous learning capabilities. |
| Approach: | They propose an agent framework with a dynamic, evolvable memory mechanism specifically designed for KG reasoning. |
| Outcome: | EvoMemKG achieves state-of-the-art performance without training or tools . it achieves improvements of up to 20% over baseline on multi-hop queries . |