Data Agents
for Complex
Data Analysis
Build autonomous AI agents that decompose complex analytical questions, orchestrate multi-step reasoning over heterogeneous data sources, and deliver accurate answers.
News & Updates
Latest announcements and important updates.
Official Website Launched
The KDD Cup 2026 competition website is now live. Stay tuned for sample data and baselines on March 15.
Why Data Agents?
Traditional Data+AI systems have made significant strides in optimizing specific tasks, but they still rely heavily on human experts to orchestrate the end-to-end pipeline. This manual orchestration is a major bottleneck, limiting the scalability and adaptability of data analysis.
We define a Data Agent as a holistic architecture designed to orchestrate Data+AI ecosystems by tackling data-related tasks through integrated knowledge comprehension, reasoning, and planning capabilities. This competition challenges you to build truly autonomous data analysis systems that go far beyond single-shot question answering.
Decompose & Plan
Break down high-level analytical questions into multi-step, executable plans autonomously.
Tool Selection & Invocation
Select and invoke appropriate tools — Python scripts, SQL queries, API calls — at each reasoning step.
Heterogeneous Data Reasoning
Reason over structured tables, unstructured documents, charts, and multi-modal data sources.
Result Synthesis
Synthesize intermediate results across multiple steps to arrive at a final, accurate answer.
Broader Impact
Robust Data Agents have the potential to revolutionize how we interact with data. They can democratize data science by enabling non-experts to perform sophisticated analyses through natural language. For enterprises, they can automate the work of data analysts and database administrators, leading to massive efficiency gains. This competition will stimulate new research in agent architectures, planning algorithms, tool use, and self-reflection for AI systems.
DataAgent-Bench
Each task in DataAgent-Bench presents a self-contained data analysis challenge. The agent receives a heterogeneous data package and a high-level natural language question, and must autonomously orchestrate a complex reasoning process to produce the final answer.
Input: Data Package
Heterogeneous, multi-modal data sources
Non-Linear Reasoning Topology
Unlike simple linear chains, real-world data analysis often requires branching (parallel sub-queries), loops (iterative refinement), and convergence (merging results from multiple paths). DataAgent-Bench captures this complexity with DAG-structured reasoning graphs.
Reasoning Topology Patterns
Each step depends on the previous step's output. Errors propagate downstream.
Parallel sub-queries across different data sources, then merge results.
Iterative refinement where the agent revisits and corrects intermediate results.
Example Task
"Our Q3 regional market analysis report identifies the region with the strongest year-over-year growth. For that region, pull the total actual sales revenue of all Electronics products from our sales database. Then, compare this figure against the quarterly sales target shown in the performance dashboard chart. Report the percentage difference."
Expected Reasoning Graph
This example demonstrates a branching pattern: after identifying the target region, the agent spawns two parallel sub-tasks (database query and chart analysis), then merges results for the final computation.
Read PDF report → identify top-growth region
Query sales WHERE region = "East Asia" AND category = "Electronics"
Read performance dashboard chart → extract Q3 target
Compute percentage difference: (4,200,000 - 3,800,000) / 3,800,000
Difficulty Levels
| Level | Steps | Data Sources | Topology |
|---|---|---|---|
| Easy | 1–2 | DB + 1 document | Linear chain |
| Medium | 2–3 | DB + 2 documents | Linear / branching |
| Hard | 4+ | DB + 3 documents (incl. image) | Branching + merging |
| PhD | 5+ | DB + multi-source, cross-referencing | DAG with loops |
Scoring & Evaluation
Our evaluation framework combines automated scoring with expert human review. The scoring system penalizes hallucination, encouraging the development of trustworthy and reliable agents. The final score is a macro-average across all questions.
Perfect
Correctly and completely answers the question with no hallucinated content.
Acceptable
Provides a useful answer but may contain minor, non-harmful errors.
Missing
The agent responds that it does not know the answer.
Incorrect
The response provides wrong or irrelevant information. Penalizes hallucination.
Two-Stage Evaluation Process
Stage 1: Automated Evaluation
Throughout the competition, a public leaderboard provides real-time feedback based on automated scoring against a hidden test set. This uses the benchmark's automatic correctness checks for immediate, objective assessment.
Stage 2: Human Evaluation
The final ranking of the top 10 teams will be determined by a panel of expert human evaluators. This ensures that the nuances of answer quality and real-world impact are properly assessed beyond what automated metrics can capture.
Competition Timeline
The competition runs from April to August 2026, with a preview release in March and two competitive phases designed to identify and challenge the strongest teams.
Sample Data & Baselines Release
Partial DataAgent-Bench examples and baseline implementations are publicly released.
Competition Officially Opens
Full dataset release, starter kit available, and public leaderboard goes live.
Phase 1: Open Competition
Open competition with public leaderboard for all registered teams.
Phase 2 Begins
Top teams from Phase 1 are invited to the final round.
Registration Freeze
Team formation and registration deadline.
Final Submission Deadline
Phase 2 ends. All final submissions must be completed.
Winners Notified
Top teams are notified of their results.
KDD 2026 Announcement
Formal announcement of winners at KDD 2026.
Awards & Recognition
We offer a substantial prize pool to encourage broad and enthusiastic participation from the global research community.
Total Prize Pool
The prize distribution among top-performing teams is to be determined. Details will be announced on this page as they are finalized.
Beyond Prizes
KDD Cup Workshop Presentation
Winning teams will have the opportunity to present their solutions at the KDD Cup Workshop at KDD 2026, a dedicated half-day session providing significant visibility for their work to the broader data mining and AI community.
Community Recognition
Top-performing teams will be recognized at the formal KDD 2026 Winners Announcement ceremony, gaining visibility among leading researchers and practitioners in the field.
Organizing Team
The organizing team is a collaboration of leading researchers from Tsinghua University and HKUST (Guangzhou), with extensive expertise in Data+AI systems, large language models, and agentic AI.
Boyan Li
Primary ContactPhD Student
HKUST (Guangzhou)
Research focuses on Text-to-SQL and Data Agents. Published 14 papers in top venues including KDD, ICML, NeurIPS, and VLDB.
Guoliang Li
Professor
Tsinghua University
ACM Fellow and IEEE Fellow. Research focuses on learning-based databases and data-centric AI. VLDB 2017 Early Research Contribution Award recipient. Served as SIGMOD 2021 General Co-Chair and ICDE 2027 PC Co-Chair.
Nan Tang
Associate Professor
HKUST (Guangzhou) & HKUST
ACM Distinguished Member. Research interests include AI4DB and data-centric AI. Recipient of the VLDB 2010 Best Paper Award and the SIGMOD 2024 Research Highlight Award. Co-organized the KDD Cup 2024 CRAG Challenge.
Yuyu Luo
Primary ContactAssistant Professor
HKUST (Guangzhou) & HKUST
Research at the intersection of Data and AI, focusing on Data Agents and Data-centric AI. 50+ publications in top-tier DB and AI venues (SIGMOD, VLDB, KDD, ICML, NeurIPS, ICLR). Best-of-SIGMOD 2023 Papers recipient. Co-organized the LLM+Vector Data Workshop at ICDE 2026, the Agentic Data System Workshop at VLDB 2026, and presented Data Agent tutorials at SIGMOD and VLDB.
Frequently Asked Questions
Sponsors & Partners
We are grateful to our sponsors for their generous support. Sponsorship details will be announced soon.
Gold Sponsors
Silver Sponsors
Interested in sponsoring KDD Cup 2026?
Contact us for sponsorship opportunities