MemoBrain: 作为推理代理的执行记忆脑
MemoBrain: Executive Memory as an Agentic Brain for Reasoning
AI总结：
MemoBrain通过构建依赖感知的记忆模型，实现对长周期推理轨迹的显式认知控制，提升工具增强代理的推理连贯性和任务对齐性。
摘要：
在工具增强的代理框架中，复杂推理本质上具有长周期特性，导致推理轨迹和临时工具产物不断积累，从而加剧大语言模型有限工作上下文的压力。没有显式记忆机制，这种积累会破坏逻辑连续性并削弱任务对齐。这表明记忆不是一种次要的效率问题，而是在长周期内维持连贯、目标导向推理的核心组件。我们提出了MemoBrain，一种为工具增强代理设计的执行记忆模型，它在推理步骤上构建了依赖感知的记忆，捕捉显著的中间状态及其逻辑关系。作为推理代理的副驾驶，MemoBrain在不阻塞执行的情况下组织推理进程，并主动管理工作上下文。具体而言，它会修剪无效步骤，折叠完成的子轨迹，并在固定上下文预算下保留一个紧凑、高显著性的推理主干。这些机制共同实现了对推理轨迹的显式认知控制，而非被动的上下文积累。我们在具有挑战性的长周期基准上评估了MemoBrain，包括GAIA、WebWalker和BrowseComp-Plus，展示了与强基线相比的一致性改进。
英文摘要：
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.
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。
