arXiv：cs.CL· Dongfang Li, Zixuan Liu, Junmai Wang, Jiahe Huang, Fuhao Li, Lin Zhang, Bonian Jia, Baotian Hu, Min Zhang·· 6 小时前
LycheeMemory V2：通过语义段级整合为 LLM 智能体提供高效长期记忆
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
AI 导读
LycheeMemory V2 用语义段级整合替代逐轮整合，将多轮对话批量编码为上下文无关的类型化记忆记录，降低 LLM 编码频率并保留事件级与时序证据。在 GPT-4.1-Mini 上，它在 LoCoMo 达到 89.22%、LongMemEval-S 达到 92.20%；相比 A-Mem，构建 token 分别减少 86.0% 和 75.9%，且不增加查询期 token 消耗。
正文
Abstract: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.
| Comments: | 33 pages, 5 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.12990 [cs.CL] |
| (or arXiv:2608.12990v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.12990 arXiv-issued DOI via DataCite |
Submission history
From: Dongfang Li [view email]
[v1]
Thu, 13 Aug 2026 09:13:15 UTC (862 KB)
[v2]
Wed, 14 Oct 2026 08:00:04 UTC (860 KB)
来源：arXiv：cs.CL · arxiv.org