MemoBrain：将执行记忆作为推理的智能大脑

摘要

工具增强型智能体框架中的复杂推理本质上是长程任务，这会导致推理轨迹和临时工具产物不断累积，从而对大型语言模型的有限工作上下文造成压力。若无显式记忆机制，此类累积会破坏逻辑连续性并削弱任务对齐效果。这使得记忆不再仅是辅助性的效率考量，而成为维持长程推理中逻辑连贯与目标导向的核心组件。我们提出MemoBrain——一种面向工具增强型智能体的执行记忆模型。该模型通过构建具备依赖感知能力的记忆系统，捕获推理过程中的关键中间状态及其逻辑关联。MemoBrain作为推理智能体的协同驾驶模块，在不阻断执行流程的前提下组织推理进度，并主动管理工作上下文。具体而言，它在固定上下文预算下执行三项核心操作：剪枝无效推理步骤、折叠已完成子轨迹、保留紧凑的高显著性推理主干。这些机制共同实现了对推理轨迹的显式认知控制，而非被动的上下文堆积。我们在GAIA、WebWalker和BrowseComp-Plus等具有挑战性的长程基准测试上评估MemoBrain，实验结果表明该方法相较强基线模型取得了一致性提升。

English

Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory mechanisms, such accumulation disrupts logical continuity and undermines task alignment. This positions memory not as an auxiliary efficiency concern, but as a core component for sustaining coherent, goal-directed reasoning over long horizons. We propose MemoBrain, an executive memory model for tool-augmented agents that constructs a dependency-aware memory over reasoning steps, capturing salient intermediate states and their logical relations. Operating as a co-pilot alongside the reasoning agent, MemoBrain organizes reasoning progress without blocking execution and actively manages the working context. Specifically, it prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget. Together, these mechanisms enable explicit cognitive control over reasoning trajectories rather than passive context accumulation. We evaluate MemoBrain on challenging long-horizon benchmarks, including GAIA, WebWalker, and BrowseComp-Plus, demonstrating consistent improvements over strong baselines.

MemoBrain：将执行记忆作为推理的智能大脑

MemoBrain: Executive Memory as an Agentic Brain for Reasoning

摘要

Support