TrawMem：把智能体记忆重构为任务导向的角色自适应工作区
TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces
一篇新的智能体记忆论文，TrawMem 不按相关性检索，而是按记忆在任务里的角色来组织，在 LoCoMo 上跑赢了 SimpleMem 还更省 token，做 Agent 记忆的可以看看。
论文 TrawMem 提出按任务角色组织记忆的工作区机制，将交互历史整理为局部线程，再联合挑选互补记忆。在 LoCoMo 和 MemGallery 两个基准上，配合 4 个开源与闭源骨干模型，macro-F1 提升 2.23-3.14 点。在 LoCoMo 上，相比 SimpleMem，TrawMem 在 Qwen3.5-9B 和 DeepSeek-V4-Flash 上的 LLM-Judge 分数分别提高 4.07 和 4.31 个百分点，同时上下文 token 分别少用约 12.8% 和 5.1%。
TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces
Large language model (LLM) agents rely on memory systems to leverage long-term interactions, yet existing systems typically retrieve memories based on their relevance to the current query and use them as contextual evidence. However, relevance alone does not characterize how a memory contributes to task solving: the same memory may serve different roles across tasks, such as directly supporting the answer or linking to complementary memories with weaker semantic relevance but necessary information. We therefore reframe agent memory systems as Task-Oriented Role-Adaptive Workspaces, where memories are selected and organized by their task-oriented roles and relations. Based on this view, we propose TrawMem, which organizes interaction histories into local threads and constructs task-oriented workspaces by assigning roles and jointly selecting complementary memories. Experiments on LoCoMo and MemGallery with four open- and closed-source backbones show consistent improvements over representative memory systems, with macro-F1 gains of 2.23-3.14 points. On LoCoMo, TrawMem improves the LLM-Judge score over SimpleMem by 4.07 and 4.31 percentage points on Qwen3.5-9B and DeepSeek-V4-Flash, respectively, while requiring approximately 12.8% and 5.1% fewer context tokens, respectively.