DBScholar

Back to papers

AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries

Summary: AOP: first system for automated, interactive LLM pipeline orchestration on data lakes; defines reusable semantic operators (retrieval, filter, aggregate, validate) to assemble multi‑step workflows across unstructured, semi‑structured, and structured data. LLM‑driven operator extraction plus pipeline optimizations (prefetching, parallelism, interactive self‑reflection) yields large accuracy gains (≈45%) on complex query benchmarks. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
h02e0a1703b7892be
Venue
CIDR
Year
2025
Pagerank
6.7814795e-05
Overall Rank
4,142 | 72.16%
DOI
-

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{wang_cidr25,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '25},
        title = {{AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Wang, Jiayi and Li, Guoliang},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 15 of 15 citing papers.

Rank Citing Paper Year Venue Pagerank
4,385 R-Bot: An LLM-based Query Rewrite System 2025 VLDB 6.6235293e-05
6,379 Unify: A System For Unstructured Data Analytics 2025 VLDB 5.8083127e-05
6,886 Multi-Objective Agentic Rewrites for Unstructured Data Processing 2026 VLDB 5.6551172e-05
7,885 Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems 2025 VLDB 5.433531e-05
8,997 Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees 2026 SIGMOD 5.2410834e-05
10,144 Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics 2026 CIDR 5.0715586e-05
10,422 Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data 2026 SIGMOD 4.9793485e-05
10,690 Task Cascades for Efficient Unstructured Data Processing 2026 SIGMOD 4.9793485e-05
10,738 OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision 2026 VLDB 4.9793485e-05
10,791 BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents 2026 VLDB 4.9793485e-05
10,845 Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees 2026 VLDB 4.9793485e-05
10,978 CADENZA in Action: Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries 2026 VLDB 4.9793485e-05
10,983 Policy-Aware Federated Query Orchestration Across Energy Data Spaces and Edge AI Services 2026 VLDB 4.9793485e-05
11,034 Data Agents: Rethinking Data Systems in the AI Agent Era 2026 VLDB 4.9793485e-05
13,609 Data Management for Agentic Memory: Foundations, Systems, and Challenges 2026 VLDB -
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 7 of 7 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers