LycheeMemory V2：基于语义片段级整合的高效LLM智能体长期记忆机制

摘要

长视野LLM智能体必须保留过往交互中的信息以支持未来任务。现有记忆系统通常依赖即时整合机制，在每次交互后调用LLM来提取、总结或更新记忆。这种设计导致随着对话增长，记忆构建成本不断攀升。粗粒度的摘要可以降低构建成本，但可能丢弃细粒度的上下文证据，而更大的检索上下文或多跳LLM推理则将开销转移到查询阶段。我们提出LycheeMemory V2，一种高效的长时记忆框架，将回合级整合替换为语义片段级整合。LycheeMemory不对每次交互进行整合，而是将多次交互批量打包为片段，并将每个已完成的片段编码为上下文无关的类型化记忆记录。片段级批量处理降低了LLM编码频率，而语义边界检测相比固定窗口批量处理，有助于保留连贯的事件级和时间级证据。生成的记录通过轻量级结构化索引组织，以支持查询规划的证据检索。使用GPT-4.1-Mini的实验表明，LycheeMemory达到了最先进的性能，在LoCoMo上达到89.22%，在LongMemEval-S上达到92.20%。与A-Mem相比，它在LoCoMo上将构建token减少86.0%，在LongMemEval-S上减少75.9%，且没有增加查询时的token用量。更广泛地说，我们的结果表明，长时智能体记忆的准确率-成本权衡不仅取决于保留了什么信息，还取决于信息整合的粒度。

English

Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories. This design makes memory construction increasingly costly as conversations grow. Coarse summarization can reduce construction cost but risks discarding fine-grained contextual evidence, whereas larger retrieval contexts or multi-hop LLM reasoning shift the overhead to query time. We present LycheeMemory V2, an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation. Instead of consolidating every interaction, LycheeMemory batches multiple exchanges into segments and encodes each finalized segment into context-independent typed memory records. Segment-level batching lowers LLM encoding frequency, while semantic boundary detection helps preserve coherent event-level and temporal evidence compared with fixed-window batching. The resulting records are organized with lightweight structured indexes for query-planned evidence retrieval. Experiments using GPT-4.1-Mini show that LycheeMemory achieves state-of-the-art performance, reaching 89.22% on LoCoMo and 92.20% on LongMemEval-S. Compared with A-Mem, it reduces construction tokens by 86.0% on LoCoMo and 75.9% on LongMemEval-S without increasing query-time token usage. More broadly, our results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated.