SumOne：即插即用的智能体记忆摘要器
SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory
给长程智能体做上下文压缩的论文，训练一次就能即插即用，DeepSearchQA 和 SWE-bench 上省七成多推理成本，几乎不掉分。
arXiv 论文提出 SumOne，一个独立的轻量摘要器，用掩码重建方式从原始轨迹自监督训练，配合 GRPO 优化，不需要参考摘要或下游任务执行。推理时只保留摘要器本身，可即插即用地压缩智能体上下文。在 DeepSearchQA 上推理成本约降低 78%，在 SWE-bench Verified 上约降低 75%，绝对分数下降仅 0.04。同一 checkpoint 可跨下游模型和智能体框架迁移，无需额外微调。
SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory
Long-horizon language-model agents accumulate increasingly large interaction histories, making context compaction essential for efficient execution. Existing learned compaction methods often rely on downstream task outcomes or solver behavior, coupling training to specific tasks or agents. We introduce SumOne, a standalone summarizer trained to preserve information in agent histories through masked reconstruction. Given a summary of the expired history, a frozen reconstructor recovers randomly masked portions of the original trajectory; reconstruction quality, combined with a length penalty, provides a task-agnostic reward for optimizing the summarizer with GRPO. This yields self-supervision directly from raw trajectories, without reference summaries or downstream task execution. At inference time, only the lightweight summarizer is retained, enabling plug-and-play context compression for otherwise unchanged agents. We conduct a systematic evaluation of SumOne in long-horizon search and software-engineering tasks. SumOne reduces estimated inference cost by approximately 78\% on DeepSearchQA and 75\% on SWE-bench Verified relative to operating with full context, with absolute decreases of 0.04. The same checkpoint also transfers across downstream models and agent harnesses without additional fine-tuning.