这篇新论文把智能体常栽跟头的上下文问题拆成五个可操作的原语，还给出了验证方案，在LongMemEval和LoCoMo上分别跑了92%和93.2%。
论文提出Agentic Context Management框架，将上下文管理分解为五个原语：架构、注入、范围、预测和压缩。传统的累积式上下文管理使token成本随对话长度平方增长，而粗粒度的摘要化虽使成本线性但精度下降。该框架通过基于保真度验证的压缩，在LongMemEval上达到92%，在LoCoMo上达到93.2%。该研究为生产环境中智能体的上下文管理提供了结构化方法。
// Agentic Context Management // Great read for the weekend. (bookmark it) Production agents fail...
// Agentic Context Management // Great read for the weekend. (bookmark it) Production agents fail less on reasoning and more on what sits in their context. Conversation history, big prompts, huge tool definitions, and ballooning tool outputs pile up every turn. The common response is storage and retrieval, a place to stash memories and look them up. New research argues that framing is too narrow and names a fuller discipline, Agentic Context Management. It decomposes into five primitives, architecting, ingesting, scoping, anticipating, and compacting with consolidation. Naive accumulation grows token cost with the square of conversation length. Crude summarization buys linear cost but hits an accuracy cliff. Only compaction validated against fidelity gets you linear cost without losing what matters. A reference implementation reports 92% on LongMemEval and 93.2% on LoCoMo. Why does it matter? Context management is becoming a first-class production concern that operates across an entire organization. The five primitives give you a structured way to reason about where your token budget goes. Paper: arxiv.org/abs/2607.21503 Learn to build effective AI agents in our academy: academy.dair.ai 💬 3 🔄 6 ❤️ 23 👀 2930 📊 13 ⚡
- arXiv cs.AI07-23 16:51原文