AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation
Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generalization ability of these memory designs, which highlights the need for a more flexible, learning-based memory framework. In this paper, we propose AtomMem, which reframes memory management as a dynamic decision-making problem. We deconstruct high-level memory processes into fundamental atomic CRUD (Create, Read, Update, Delete) operations, transforming the memory workflow into a learnable decision process. By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors tailored to specific task demands. Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods. Further analysis of training dynamics shows that our learning-based formulation enables the agent to discover structured, task-aligned memory management strategies, highlighting a key advantage over predefined routines.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
Large language models (LLMs) demonstrate strong reasoning and generation abilities, but their fixed context windows limit long-term information accumulation and reuse across multi-session interactions. Existing memory-au…
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms…
Reinforcement LearningEgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in existing systems: indices built from context-poor captions…
Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA training methods suffer from two critical …
Toward a Theory of Hierarchical Memory for Language Agents
Many recent long-context and agentic systems address context-length limitations by adding hierarchical memory: they extract atomic units from raw data, build multi-level representatives by grouping and compression, and t…