arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.01599cs.AI
收藏

ByteRover:通过LLM-curated分层上下文实现代理原生内存

ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context

ByteRover

Andy Nguyen, Danh Doan, Hoang Pham, Bao Ha, Dat Pham, Linh Nguyen, Hieu Nguyen, Thien Nguyen, Cuong Do, Phat Nguyen, Toan Nguyen

AI总结:

本文提出ByteRover,一种代理原生内存架构,通过LLM-curated分层上下文实现知识的结构化存储与检索,实验显示其在LoCoMo和LongMemEval上表现优异,无需外部基础设施。

摘要:

记忆增强生成(MAG)通过外部内存扩展大语言模型以支持长上下文推理,但现有方法普遍将内存视为外部服务,导致知识存储与理解脱节,产生语义漂移、协调失效等问题。本文提出ByteRover,一种代理原生内存架构,通过LLM-curated分层上下文实现知识的结构化存储与检索。ByteRover采用分层上下文树表示知识,以领域、主题、子主题和条目组织为文件化的知识图谱,其中每个条目包含显式关系、溯源信息和自适应知识生命周期(AKL)管理,包括重要性评分、成熟度层级和时效衰减。检索采用五级递进策略,大部分查询可在亚100毫秒内完成,无需LLM调用,仅在遇到新问题时升级到代理推理。实验表明,ByteRover在LoCoMo和LongMemEval上分别达到最先进的准确率和竞争性结果,且无需外部基础设施,如向量数据库、图数据库或嵌入服务,所有知识存储为人类可读的markdown文件在本地文件系统中。

英文摘要:

Memory-Augmented Generation (MAG) extends large language models with external memory to support long-context reasoning, but existing approaches universally treat memory as an external service that agents call into, delegating storage to separate pipelines of chunking, embedding, and graph extraction. This architectural separation means the system that stores knowledge does not understand it, leading to semantic drift between what the agent intended to remember and what the pipeline actually captured, loss of coordination context across agents, and fragile recovery after failures. In this paper, we propose ByteRover, an agent-native memory architecture that inverts the memory pipeline: the same LLM that reasons about a task also curates, structures, and retrieves knowledge. ByteRover represents knowledge in a hierarchical Context Tree, a file-based knowledge graph organized as Domain, Topic, Subtopic, and Entry, where each entry carries explicit relations, provenance, and an Adaptive Knowledge Lifecycle (AKL) with importance scoring, maturity tiers, and recency decay. Retrieval uses a 5-tier progressive strategy that resolves most queries at sub-100 ms latency without LLM calls, escalating to agentic reasoning only for novel questions. Experiments on LoCoMo and LongMemEval demonstrate that ByteRover achieves state-of-the-art accuracy on LoCoMo and competitive results on LongMemEval while requiring zero external infrastructure, no vector database, no graph database, no embedding service, with all knowledge stored as human-readable markdown files on the local filesystem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑