发表机构
The Pennsylvania State University（宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对长上下文场景下压缩器丢失会话约束（SCs）的问题，提出COMPINT评估套件量化损失，并开发即插即用的SCs感知提取器，使SCs保留率超90%。
AI 中文摘要
当上下文窗口面临压力时，大语言模型（LLM）系统会压缩先前的上下文以继续进行当前任务。我们识别出一类用户发出的指令，即会话约束（Session Constraints, SCs），例如“在我确认之前不要删除任何邮件”，这类指令旨在约束LLM在会话剩余时间内的行为，但在压缩过程中会被悄然丢弃。为量化这种损失，我们引入了COMPINT评估套件，该套件在三种长上下文场景下对压缩器进行评估：多轮对话、智能体轨迹以及长周期研究。当前压缩器平均仅保留17%的注入SCs，且大多数压缩器的性能比不进行压缩执行相同任务时更差。保留率随压缩器、提示、上下文长度、SCs措辞以及注入位置的变化而大幅波动，表明这种损失是系统性的，而非与任何单一设置相关。我们提出了一种感知SCs的提取器，该提取器作为即插即用模块与压缩器协同运行，在不修改压缩器或LLM的情况下，在所有三种场景中实现了超过90%的保留率。COMPINT评估套件及配套实现可在该httpsURL获取。
英文摘要
When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instructions, Session Constraints (SCs), such as "do not delete any emails until I confirm," that are meant to constrain LLM's behavior for the remainder of a session but are silently dropped during compaction. To quantify this loss, we introduce COMPINT, an evaluation suite that evaluates compactors across three long-context scenarios: multi-turn chat, agentic trajectory, and long-horizon research. Current compactors retain only 17% of injected SCs on average, and most perform worse than running the same task without compaction. Retention varies sharply with compactor, prompt, context length, SC phrasing, and injection location, showing that the loss is systematic rather than tied to any single setting. We propose an SC-aware extractor that runs alongside the compactor as a plug-and-play module, achieving over 90% retention across all three scenarios without modifying the compactor or LLM. The COMPINT evaluation suite and accompanying implementation are available at https://github.com/ZhiqiEliWang/compaction-integrity.
