Search papers, labs, and topics across Lattice.
The paper introduces the Long-horizon Memory Embedding Benchmark (LMEB) to evaluate memory embeddings in long-horizon retrieval tasks, addressing the limitations of existing benchmarks focused on traditional passage retrieval. LMEB comprises 22 datasets and 193 zero-shot tasks across episodic, dialogue, semantic, and procedural memory types, using both AI-generated and human-annotated data. Experiments with 15 embedding models reveal that LMEB presents a reasonable challenge, larger models don't always perform better, and LMEB is orthogonal to MTEB, highlighting the need for specialized models for long-horizon memory retrieval.
Traditional text embedding benchmarks fail to capture the nuances of long-horizon memory retrieval, but this new benchmark reveals that bigger models don't always win, and performance on standard tasks doesn't guarantee success in complex, context-dependent memory scenarios.
Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models'ability to handle long-horizon memory retrieval tasks involving fragmented, context-dependent, and temporally distant information. To address this, we introduce the Long-horizon Memory Embedding Benchmark (LMEB), a comprehensive framework that evaluates embedding models'capabilities in handling complex, long-horizon memory retrieval tasks. LMEB spans 22 datasets and 193 zero-shot retrieval tasks across 4 memory types: episodic, dialogue, semantic, and procedural, with both AI-generated and human-annotated data. These memory types differ in terms of level of abstraction and temporal dependency, capturing distinct aspects of memory retrieval that reflect the diverse challenges of the real world. We evaluate 15 widely used embedding models, ranging from hundreds of millions to ten billion parameters. The results reveal that (1) LMEB provides a reasonable level of difficulty; (2) Larger models do not always perform better; (3) LMEB and MTEB exhibit orthogonality. This suggests that the field has yet to converge on a universal model capable of excelling across all memory retrieval tasks, and that performance in traditional passage retrieval may not generalize to long-horizon memory retrieval. In summary, by providing a standardized and reproducible evaluation framework, LMEB fills a crucial gap in memory embedding evaluation, driving further advancements in text embedding for handling long-term, context-dependent memory retrieval. LMEB is available at https://github.com/KaLM-Embedding/LMEB.