长时任务里AI老忘事？这篇提出主动记忆智能体，随跑随记关键信息，在Terminal-Bench上提升8.3pp，比被动记忆好用多了。
研究提出行为状态衰减概念，指长时任务中决策相关信息被淹没在轨迹中。一个独立的记忆智能体与行动智能体并行运行，更新结构化的记忆库并选择性注入提醒。在Terminal-Bench 2.0和τ²-Bench上，该方法将pass@1分别提升8.3和6.8个百分点。消融实验表明选择性干预优于被动暴露或持续注入。作为开放权重记忆策略的初步工作，在SETA上使用SFT和GRPO训练Qwen3.5-27B，提升验证奖励并部分迁移到Terminal-Bench。
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the recent trajectory and deciding whether to inject a memory-grounded reminder or remain silent. The module is plug-and-play with frontier action agents and existing agent harnesses. Across Terminal-Bench 2.0 and $τ^2$-Bench, it improves pass@1 for both weaker and stronger action agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on $τ^2$-Bench. Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retrieval. As an early step toward open-weight memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench.