Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus· Agent的历史能预测压缩何时会损害性能吗？
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts when a compaction will hurt. TRACE's public corpus of 590 harness-triggered AppWorld compaction boundaries replays each boundary from a re-executed prefix state under the pre-compaction context and under the summary, and records the burden of the next actions: calls that error or repeat a call already made. We find that pre-boundary history predicts post-compaction harm only weakly. An internally prespecified contrast by prefix placement is a wide null, and the naive "has-written" label behind it turns out to measure trajectory phase. The best extension-protocol trigger reaches held-out AUROC 0.66 (0.64 on the repli
研究压缩对Agent性能的影响及预测可能性
- 核心方法
- 通过分析TRACE公共数据集中590个由Harness触发的AppWorld压缩边界前后的行为，评估压缩对后续操作负担的影响
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 压缩Agent上下文时，如何判断压缩是否会对性能产生负面影响
- 关键实验
- 实验分析了压缩前后错误调用或重复调用的频率，使用内部预设对比测试了不同触发机制的效果
- 主要贡献
- 提出并验证了基于Agent历史行为预测压缩负面影响的有效性及局限性
- 意义与局限
- 为长期Agent上下文管理策略提供了实验依据，但预测效果较弱，表明更复杂的方法可能需要被开发