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 |
|---|---|---|---|---|
| 630 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB | 0.00015402076 |
| 697 | Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing | 2025 | CIDR | 0.00014665686 |
| 10,432 | Making Prompts First-Class Citizens for Adaptive LLM Pipelines | 2026 | CIDR | 4.9605343e-05 |
Previous
Page 1 / 1
Next