发表机构
University of Virginia; Nokia（弗吉尼亚大学; 诺基亚）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长时程智能体，提出PAIR方法，通过反事实延续定位并修正有害压缩事件，提升压缩执行的跨运行可靠性，接近甚至超越无压缩基线。
AI 中文摘要
长时程智能体需要上下文压缩来管理不断增长的交互历史。然而，压缩质量最终由下游执行决定。现有的提示适配方法通过比较全上下文与压缩轨迹来推断压缩错误。此类比较无法隔离单个压缩的影响，且会受到智能体随机性的干扰。我们首先发现压缩在损害可解性之前先降低了可靠性。通过使用匹配的反事实延续——在同一智能体状态下比较有无压缩的执行情况——我们进一步表明，严重退化集中在孤立的压缩事件上。基于这一发现，我们提出了PAIR（使用干预式回放的提示适配）方法来适配结构化压缩提示。PAIR识别出导致后续执行退化的单个压缩，诊断其影响，并修正固定压缩模板的相关部分。在所有主要基准-范围组合中，PAIR在压缩方法中实现了最强的跨运行可靠性，持续超过竞争性的提示适配基线。在不修改下游智能体的情况下，PAIR使压缩执行接近无压缩基线，有时在数值上甚至超过它。
英文摘要
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing prompt-adaptation methods infer compression errors by comparing full-context and compressed trajectories. Such comparisons cannot isolate individual compressions and are confounded by agent stochasticity. We first find that compression degrades reliability before solvability. Using matched counterfactual continuations that compare execution from the same agent state with versus without compression, we further show that severe degradation concentrates at isolated compression events. Motivated by this finding, we propose PAIR (Prompt Adaptation using Interventional Rollouts) for adapting structured compression prompts. PAIR identifies individual compressions that degrade subsequent execution, diagnoses their effects, and revises the relevant sections of a fixed compression template. PAIR achieves the strongest cross-run reliability among compressed methods in every main benchmark-scope combination, consistently exceeding the competing prompt-adaptation baseline. Without modifying the downstream agent, PAIR brings compressed execution close to the no-compression baseline and sometimes numerically exceeds it.
Comments41 pages, 10 figures, 9 tables
