Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a lightweight memory layer called persistent discovery context that enables data-centric agents to retain and reuse prior intent-to-object mappings during the discovery phase. By leveraging this memory, the agents significantly enhance retrieval quality compared to traditional metadata-only search across three structured data environments. The results reveal that in lexically sparse domains, memory-based retrieval can even surpass metadata-based methods, highlighting the potential of reusing discovery outcomes in improving agent performance.
Memory-based retrieval can outperform metadata-only approaches, revealing a surprising advantage in lexically sparse environments.
Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful discovery outcomes are typically discarded rather than reused. We introduce persistent discovery context, a lightweight memory layer that stores prior intent-to-object mappings and reuses them to augment future retrieval. Across three structured data environments, persistent discovery context consistently improves retrieval quality over metadata-only search, remains effective with automatically generated memories, and exposes a reproducible interference failure mode. In lexically sparse domains, memory-only retrieval can even outperform metadata-based retrieval. These findings suggest that discovery outcomes constitute a useful form of reusable context for data-centric agents.