CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reading ComprehensionQuestion AnsweringSimilar Papers 제목 키워드 기반
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
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 LearningA Multi-Stage Memory Augmented Neural Network for Machine Reading Comprehension
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 ComprehensionTriviaQAAttention-aware semantic relevance predicting Chinese sentence reading
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 SimilaritySentenceNeural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension
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 ComprehensionA Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models
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…