Making Prompts First-Class Citizens for Adaptive LLM Pipelines
Summary: Proposes SPEAR, treating prompts as first-class, structured, versioned artifacts integrated into execution for provenance, introspection, and reuse. Adds adaptive prompt refinement and policy-driven when‑then control to evolve prompts at runtime, unlocking optimization and integration opportunities in LLM pipelines. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Uğur Çetintemel (Brown University)
- 2. Shu Chen (Brown University)
- 3. Alexander W. Lee (Brown University)
- 4. Deepti Raghavan (Brown University)
- 5. Duo Lu (Brown University)
- 6. Andrew Crotty (Northwestern University)
BibTeX Citation
@inproceedings{cetintemel_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{Making Prompts First-Class Citizens for Adaptive LLM Pipelines}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Çetintemel, Uğur and Chen, Shu and Lee, Alexander W. and Raghavan, Deepti and Lu, Duo and Crotty, Andrew},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,957 | Credo: Declarative Control of LLM Pipelines via Beliefs and Policies | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 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 |
| 3,126 | Abacus: A Cost-Based Optimizer for Semantic Operator Systems | 2026 | VLDB | 7.6185225e-05 |
| 4,675 | spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines | 2024 | VLDB | 6.474947e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,444 | Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective | 2026 | SIGMOD |
| 2 | 6,886 | Multi-Objective Agentic Rewrites for Unstructured Data Processing | 2026 | VLDB |
| 3 | 5,149 | LLM for Data Management | 2024 | VLDB |
| 4 | 11,393 | Smart SPARQL Advisor: Guiding Users in Query Formulation with Performance Prediction | 2025 | VLDB |
| 5 | 11,061 | LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning | 2026 | VLDB |
| 6 | 4,675 | spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines | 2024 | VLDB |
| 7 | 4,142 | AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries | 2025 | CIDR |
| 8 | 8,888 | Optimized Batch Prompting for Cost-effective LLMs | 2025 | VLDB |
| 9 | 13,633 | Prompt Editor: A Taxonomy-driven System for Guided LLM Prompt Development in Enterprise Settings | 2025 | SIGMOD |
| 10 | 3,695 | Revisiting Prompt Engineering via Declarative Crowdsourcing | 2024 | CIDR |