NVIDIA 论文：上下文压缩后 Claude Opus 4.5 在 SWE-bench 上几乎不丢分
NVIDIA 推荐的论文：Opus 4.5 每步压缩上下文，SWE-bench 得分 70.2 几乎不输完整历史，峰值上下文降到 8K，还能省钱。
NVIDIA 推荐的一篇论文测试了智能体场景下的激进上下文压缩。Claude Opus 4.5 在 SWE-bench Verified 上采用每步压缩后得分 70.2，与保留完整历史的 70.0 基本持平，中位峰值上下文从 32K tokens 降到 8K。在对话结尾做简单压缩反而更好，得分从 70.0 升到 74.8。该模式在 Terminal-Bench、FRAMES、BFCLv3 和多语言 SWE-bench 上同样成立，部分设置有小幅损失。成本方面，前沿开源权重模型生成后段 token 的价格最高是前段的 7 倍。
Highly recommended paper from NVIDIA. (bookmark it) There is a lot of debate about whether to use context compaction aggressively. They show that with frequent compaction, frontier language models lose little to no accuracy on a broad range of long-horizon and long-input tasks while keeping their context short. With one action per context, Claude Opus 4.5 scores 70.2 on SWE-bench Verified against 70.0 with the full history. Median peak context drops from 32K to 8K tokens. The agent carries a short summary of its state between steps instead of the whole transcript. Simple compaction at the end of a conversation often does better than the full history, and Opus goes from 70.0 to 74.8 with it. This also matters for cost. Later tokens cost more to generate than earlier ones, up to 7x on frontier open-weight models. The pattern holds on Terminal-Bench, FRAMES, BFCLv3 and multilingual SWE-bench, with modest losses in some settings. Before paying for million-token agent runs, it's worth testing aggressive compaction on your own tasks. arxiv.org/abs/2611.05306 Chat with Paper: academy.dair.ai/papers/you-don… 💬 29 🔄 5 ❤️ 43 👀 2465 📊 36 ⚡
