# Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics

arXiv: https://arxiv.org/abs/2509.02751 · HTML: https://mlsanity.com/paper/2509.02751/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 8 of 8)

- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics](https://mlsanity.com/paper/1805.01046/) (2018)
- [Semantic Operators: A Declarative Model for Rich, AI-based Data Processing](https://mlsanity.com/paper/2407.11418/) (2024)
- [KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes](https://mlsanity.com/paper/2506.06541/) (2025)
- [CAESURA: Language Models as Multi-Modal Query Planners](https://mlsanity.com/paper/2308.03424/) (2023)
- [Physical Representation-based Predicate Optimization for a Visual Analytics Database](https://mlsanity.com/paper/1806.04226/) (2018)
- [Accelerating Approximate Aggregation Queries with Expensive Predicates](https://mlsanity.com/paper/2108.06313/) (2021)
- [Accelerating Aggregation Queries on Unstructured Streams of Data](https://mlsanity.com/paper/2308.09157/) (2023)

## Built on by (most cited first, 7 of 7)

- [Kalypso: Relational LLM Serving](https://mlsanity.com/paper/2607.23815/) (2026)
- [stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://mlsanity.com/paper/2603.03589/) (2026)
- [Towards Effective Orchestration of AI x DB Workloads](https://mlsanity.com/paper/2603.03772/) (2026)
- [Agent-Aided Design for Dynamic CAD Models](https://mlsanity.com/paper/2604.15184/) (2026)
- [Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]](https://mlsanity.com/paper/2607.10508/) (2026)
- [Fail Loudly: An Auditable Runtime for Agentic Data Analysis](https://mlsanity.com/paper/2609.32528/) (2026)
- [ML Engineering Agents - A Data Management Perspective](https://mlsanity.com/paper/2610.16919/) (2026)

## Abstract (arXiv)

With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators -- a declarative set of AI-powered data transformations with natural language specifications. However, even when optimized, these operators can be expensive to execute on millions of records and their iterator execution semantics make them ill-suited for interactive data analytics tasks. In another line of work, Deep Research systems have demonstrated an ability to answer natural language question(s) over large datasets. These systems use one or more LLM agent(s) to plan their execution, process the dataset(s), and iteratively refine their answer. However, these systems do not explicitly optimize their query plans which can lead to poor plan execution. In order for AI-driven analytics to excel, we need a runtime which combines the optimized execution of semantic operators with the flexibility and more dynamic execution of Deep Research systems. As a first step towards this vision, we build a prototype which enables Deep Research agents to write and execute optimized semantic operator programs. We evaluate our prototype and demonstrate that it can outperform a handcrafted semantic operator program and open Deep Research systems on two basic queries. Compared to a standard open Deep Research agent, our prototype achieves up to 1.95x better F1-score. Furthermore, even if we give the agent access to semantic operators as tools, our prototype still achieves cost and runtime savings of up to 76.8% and 72.7% thanks to its optimized execution.