Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 2 Sep 2026.
Builds on
12 of 18 references.
References · 12
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2024Agent Workflow Memorycited by 383
- 2022Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learningcited by 38
- 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
- 2025Knowledge Base Construction for Knowledge-Augmented Text-to-SQLcited by 9
- 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agentscited by 4
Built on by
Not cited yet.