Credo: Declarative Control of LLM Pipelines via Beliefs and Policies
Summary: Credo is a database-backed semantic control plane for adaptive LLM pipelines, representing execution state as high-level beliefs and specifying control declaratively through policies. It replaces brittle fixed flows or agentic reasoning with auditable, debuggable runtime adaptation. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Duo Lu (Brown University)
- 2. Andrew Crotty (Northwestern University)
- 3. Uğur Çetintemel (Brown University)
BibTeX Citation
@article{lu_vldb26,
title = {{Credo: Declarative Control of LLM Pipelines via Beliefs and Policies}},
author = {Lu, Duo and Crotty, Andrew and Çetintemel, Uğur},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4518--4521},
doi = {10.14778/3827998.3828054},
url = {https://doi.org/10.14778/3827998.3828054},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 683 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB | 0.00014817539 |
| 748 | Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing | 2025 | CIDR | 0.00014281926 |
| 10,353 | Making Prompts First-Class Citizens for Adaptive LLM Pipelines | 2026 | CIDR | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,284 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB |
| 2 | 10,353 | Making Prompts First-Class Citizens for Adaptive LLM Pipelines | 2026 | CIDR |
| 3 | 5,713 | Believe It or Not: Adding Belief Annotations to Databases | 2009 | VLDB |
| 4 | 10,343 | Please Don't Kill My Vibe: Empowering Agents with Data Flow Control | 2026 | CIDR |
| 5 | 10,841 | Bolt-on, Verifiable Provenance for LLM-Powered Data Processing | 2026 | VLDB |
| 6 | 11,008 | iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI) | 2026 | VLDB |
| 7 | 10,961 | SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines | 2026 | VLDB |
| 8 | 10,973 | Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents | 2026 | VLDB |
| 9 | 13,625 | Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines | 2025 | SIGMOD |
| 10 | 7,885 | Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems | 2025 | VLDB |