Long-term conversational memory is a retrieval workload classical IR was not built for: the index grows during the query stream, query types shift intra-session, and the latency budget per retrieval is sub-10 ms. Lucene-class engines treat the index as static and the query as stateless, leaving the workload's structure unexploited. AgentIR treats fusion as a per-query decision along two axes: which fusion to apply (BM25, Dense, RRF, or agent-aware RRF), and whether the ~52 ms dense channel is worth running at all. The second axis is a confidence-triggered cascade router that decides from the BM25 top-k margin alone and re-tunes across workloads without retraining. On LongMemEval (n=500), where the dense channel does add information, the cascade skips 63% of queries at parity LLM-judged accuracy (2.67x faster under two judges, paired bootstrap p>=0.88); per-qtype thresholds extend this to 5.76x under 5-fold cross-validation. On LoCoMo (n=1,982), where BM25 alone is already the strongest single system, the same trigger auto-tunes to a 100% skip rate (132x faster, +0.089 Hit@5). Capacity on a shared 8-core VM rises from ~154 to ~1,400 concurrent agents (9x). Underneath the cascade, a time-partitioned index does O(log 1/epsilon) work independent of corpus size: 1234x corpus growth costs only 3.6x latency, ending in 1769x over sequential at sub-100 us p50 on 5M records. At parity quality with Lucene on 9 BEIR datasets up to 8.8M docs, the substrate runs 10x geo-mean over Pyserini 8T and 11x over PISA-1T BlockMax-WAND; an A100 reaches 1.8-39x over Pyserini 8T; chunked index build sustains 56.8K docs/sec on MS MARCO. Three subtle BM25/GPU correctness pitfalls that silently regress nDCG@10 by 6-8x are documented and fixed; post-fix CPU and GPU agree within 0.0002 nDCG@10 on all eight datasets that fit a single A100.

翻译：长期对话记忆是一种传统信息检索系统未曾设计的检索工作负载：索引在查询流中持续增长，查询类型在会话内动态变化，每次检索的延迟预算低于10毫秒。基于Lucene的引擎将索引视为静态、查询视为无状态，未能利用工作负载的结构特性。AgentIR将融合策略视为沿两个维度的逐查询决策：采用何种融合方式（BM25、稠密检索、RRF或智能体感知RRF），以及是否值得运行约52毫秒的稠密检索通道。第二个维度采用置信度触发的级联路由器，仅通过BM25的top-k间隔进行决策，并能在不同工作负载间自适应调整而无需重新训练。在LongMemEval数据集（n=500）上，当稠密通道确实提供信息增益时，该级联机制在LLM评判准确率持平的情况下跳过了63%的查询（在双评判器下速度提升2.67倍，配对bootstrap检验p≥0.88）；基于查询类型的阈值调整在五折交叉验证下将加速比提升至5.76倍。在LoCoMo数据集（n=1,982）上，当BM25本身已是最强单一系统时，同一触发机制自动调整至100%跳过率（速度提升132倍，Hit@5提升0.089）。共享8核虚拟机的容量从约154个提升至约1,400个并发智能体（9倍）。在级联机制底层，时间分区索引的计算复杂度为O(log 1/ε)，与语料库规模无关：1234倍语料增长仅带来3.6倍延迟增长，最终在500万条记录上实现比顺序扫描快1769倍的性能，p50延迟低于100微秒。在最高880万文档的9个BEIR数据集上，本基座在保持与Lucene同等质量的同时，几何平均速度分别为Pyserini 8T的10倍和PISA-1T BlockMax-WAND的11倍；A100 GPU上达到Pyserini 8T的1.8-39倍；在MS MARCO上分块索引构建持续维持56.8K文档/秒的处理速度。本文记录并修复了三个微妙但会导致nDCG@10降低6-8倍的BM25/GPU正确性陷阱；修复后，在单块A100可容纳的全部八个数据集上，CPU与GPU的nDCG@10差异不超过0.0002。