发表机构
University of Michigan（密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ContextRender通过执行依赖图管理LLM智能体上下文，利用工具流分析追踪结果重用，在固定预算下选择历史，提升任务性能并降低推理成本。
AI 中文摘要
执行长时程任务的LLM智能体会积累工具结果，后续步骤可能需要这些结果。即使完整历史记录在上下文窗口内，将全部历史传递给每次调用也是昂贵的，而减少历史则可能遗漏所需信息。现有的上下文管理方法可能忽略早期工具结果在后续执行中的使用方式，导致所需信息被排除在上下文之外。我们提出了ContextRender，它通过一个持久化的执行依赖图来管理上下文。我们开发了工具流分析（Tool-Flow Analysis）来追踪后续操作如何重用早期工具结果中的信息，提供一种称为“观察到的重用”（observed reuse）的信号。一个渲染器将该信号与近期性和语义相关性相结合，在固定的历史预算内选择结果，并将被遗漏的结果保留以供后续使用。在AppWorld和8目标问答（8-objective QA）上，结合三种执行模型，ContextRender在6K历史预算下优于所评估的上下文管理基线，该预算远低于模型的最大上下文窗口。在此预算内，它实现了接近或高于传递完整历史的任务性能，同时相对于完整历史将平均推理成本降低了10.2%-32.2%。消融实验表明，观察到的重用提高了任务性能以及后续重用结果的保留率。
英文摘要
LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even when it fits within the context window, while reducing it risks omitting needed information. Existing context management methods can overlook how earlier tool results are used in subsequent execution, leaving needed information out of context. We introduce ContextRender, which manages context through a persistent graph of execution dependencies. We develop Tool-Flow Analysis to track how later operations reuse information from earlier tool results, providing a signal called observed reuse. A renderer combines this signal with recency and semantic relevance to select results within a fixed history budget, retaining omitted results for later use. Across AppWorld and 8-objective QA with three execution models, ContextRender outperforms the evaluated context management baselines using a 6K history budget, well below the models' maximum context windows. Within this budget, it achieves task performance close to or above that of passing the full history while reducing mean inference cost by 10.2%-32.2% relative to Full history. Ablations show that observed reuse improves task performance and retention of results reused later.
