ArborMem：用记忆森林导航交互状态
ArborMem: Navigating Interaction States with Memory Forests
浏览论文内容
中文总结 AI 辅助
ArborMem是一种在线记忆框架，将对话表示为可导航的交互状态森林，在LongMemEval等基准上优于最强基线，还引入了分支结构诊断基准BranchMemEval。
中文摘要 AI 辅助
大型语言模型日益成为持久的对话助手，需要能保留相关经验并维持跨对话连续性的记忆。现有方法通过长上下文处理、选择性检索和结构化记忆组织提升对话历史的访问效率，但多数系统将记忆访问视为检索相关过往信息，未先确定当前轮次恢复的是哪一先前交互状态。当对话穿插多个可能被中断后重新访问的任务、人物和计划时，这一局限尤为突出。我们提出ArborMem，这是一种在线记忆框架，将长期运行的对话表示为可导航的交互状态森林：每个分支保留局部连贯的轨迹，而森林则维护多个可后续恢复的轨迹。对于每个新输入，ArborMem会定位相关状态，恢复其分支局部上下文，并补充从各分支检索到的可复用证据，在不混淆语义相关但结构不同轨迹的前提下维持交互连续性。现有长期记忆基准涵盖多种记忆与推理能力，但未明确分离分支结构相关挑战，因此我们引入BranchMemEval，这是一个针对穿插式和可恢复交互轨迹的受控诊断基准。在LongMemEval、LoCoMo、BEAM 100K和BranchMemEval上的实验显示，ArborMem在三个已建立的基准上比最强基线高出3.36至10.31个百分点，在BranchMemEval上高出5.0个百分点；其优势在受限读取预算下会进一步增大，且完整记忆查询耗时仍低于0.5秒。
英文摘要
Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localizes the relevant state, restores its branch-local context, and augments it with reusable evidence retrieved across branches, preserving interaction continuity without conflating semantically related but structurally distinct trajectories. Existing long-term memory benchmarks cover diverse memory and reasoning capabilities but do not explicitly isolate branch-structured challenges. We therefore introduce BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. Experiments on LongMemEval, LoCoMo, BEAM 100K, and BranchMemEval show that ArborMem outperforms the strongest baselines by 3.36 to 10.31 percentage points on the three established benchmarks and by 5.0 points on BranchMemEval. Its advantage grows under constrained read budgets, while complete memory queries remain below half a second.
