I benchmarked raw chat history, vector-only RAG, and a context graph on the same multi-agent conversations. The results exposed a surprising weakness in relational retrieval.
Summary generated by The Flow from the publisher's feed. The full article lives at Towards Data Science.
arXiv:2606. 00610v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge.
arXiv:2607. 26520v1 Announce Type: cross Abstract: Conversational AI agents commonly lack persistent memory across sessions.
arXiv:2602. 03315v2 Announce Type: replace Abstract: Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks.
arXiv:2607. 19359v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving multi-hop association largely unmeasured.
Conversational AI agents commonly lack persistent memory across sessions. The obvious fixes like injecting full chat histories into the context window, or delegating to a third-party memory service, either exhaust the model's context budget or send personal data through infrastructure the user does not control.
Increasing context size in RAG systems doesn’t improve accuracy for aggregation tasks—it makes errors harder to detect. In this article, I benchmark retrieval-based pipelines against a deterministic full-scan engine across 100,000 rows and show why computation queries must be routed away from RAG entirely.