Database Paper Browser

Back to papers

Intelligent Agents for Data Exploration

Summary: Surveys RL-based agents for incremental data exploration—operators, hand-crafted rewards, and task-specific successes. Positions LLM-powered agents vs RL on an automation–control spectrum, argues LLMs may reduce retraining and enable more general planner-like exploration while highlighting open tradeoffs. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13696
Venue
VLDB
Year
2024
Pagerank
4.3702863e-05
Overall Rank
9,219 | 35.87%
DOI
10.14778/3685800.3685913

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank Citing Paper Year Venue Pagerank
10,784 Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models 2025 VLDB 4.1945683e-05
10,860 Exploring Exploratory Querying 2025 VLDB 4.1945683e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

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

Rank Cited Paper Year Venue Pagerank
1,993 Automatically Generating Data Exploration Sessions Using Deep Reinforcement Learning 2020 SIGMOD 9.8453334e-05
4,874 Approximation Schemes for Many-Objective Query Optimization 2014 SIGMOD 5.8594632e-05
5,472 Guided Exploration of User Groups 2020 VLDB 5.4888146e-05
7,222 Guided Exploration of Data Summaries 2022 VLDB 4.797186e-05
11,394 EDA4SUM: Guided Exploration of Data Summaries 2022 VLDB 4.1945683e-05
Previous Page 1 / 1 Next

Semantically Similar Papers