paper-with-me

홈 › Papers

CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

2025-10-07 · Rui Li, Zeyu Zhang, Xiaohe Bo, Zihang Tian, Xu Chen, Quanyu Dai, Zhenhua Dong, Ruiming Tang arxiv

Current Large Language Models (LLMs) are confronted with overwhelming information volume when comprehending long-form documents. This challenge raises the imperative of a cohesive memory module, which can elevate vanilla LLMs into autonomous reading agents. Despite the emergence of some heuristic approaches, a systematic design principle remains absent. To fill this void, we draw inspiration from Jean Piaget's Constructivist Theory, illuminating three traits of the agentic memory -- structured schemata, flexible assimilation, and dynamic accommodation. This blueprint forges a clear path toward a more robust and efficient memory system for LLM-based reading comprehension. To this end, we develop CAM, a prototype implementation of Constructivist Agentic Memory that simultaneously embodies the structurality, flexibility, and dynamicity. At its core, CAM is endowed with an incremental overlapping clustering algorithm for structured memory development, supporting both coherent hierarchical summarization and online batch integration. During inference, CAM adaptively explores the memory structure to activate query-relevant information for contextual response, akin to the human associative process. Compared to existing approaches, our design demonstrates dual advantages in both performance and efficiency across diverse long-text reading comprehension tasks, including question answering, query-based summarization, and claim verification.

📄 PDF Abstract BibTeX arXiv:2510.05520

Code (0)

등록된 구현이 없습니다.

Tasks

Reading ComprehensionQuestion Answering

Similar Papers 제목 키워드 기반

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading

2026-05-11 · Baibei Ji, Xiaoyang Weng, Juntao Li, Zecheng Tang 외 arxiv

To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly…

Reinforcement Learning

A Multi-Stage Memory Augmented Neural Network for Machine Reading Comprehension

2018-07-01 · WS 2018 7 · Seunghak Yu, Sathish Reddy Indurthi, Seohyun Back, Haejun Lee

Reading Comprehension (RC) of text is one of the fundamental tasks in natural language processing. In recent years, several end-to-end neural network models have been proposed to solve RC tasks. However, most of these mo…

Machine Reading ComprehensionQuestion AnsweringReading ComprehensionTriviaQA

Attention-aware semantic relevance predicting Chinese sentence reading

2024-03-27 · Kun Sun

In recent years, several influential computational models and metrics have been proposed to predict how humans comprehend and process sentence. One particularly promising approach is contextual semantic similarity. Inspi…

Semantic SimilaritySemantic Textual SimilaritySentence

Neural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension

2019-09-01 · RANLP 2019 9 · Denis Smirnov

State-of-the-art machine reading comprehension models are capable of producing answers for factual questions about a given piece of text. However, some type of questions requires commonsense knowledge which cannot be inf…

Machine Reading ComprehensionReading Comprehension

A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models

2026-04-29 · Rei Emura, Saku Sugawara arxiv

Language models (LMs) behave more like humans when their cognitive resources are restricted, particularly in predicting sentence processing costs such as reading times. However, it remains unclear whether such constraint…