Credo: Declarative Control of LLM Pipelines via Beliefs and Policies

Duo Lu; Andrew Crotty; Uğur Çetintemel

cs.AIApr 15, 2026

Credo: Declarative Control of LLM Pipelines via Beliefs and Policies

Authors: Duo Lu, Andrew Crotty, Uğur Çetintemel

Organizations: Brown University · Northwestern University

Abstract

Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions. As such, correctness depends not only on the output of individual model calls, but also on how to best adapt when incorporating new evidence or revising prior conclusions. However, existing frameworks rely on imperative control loops, ephemeral memory, and prompt-embedded logic, making agent behavior opaque, brittle, and difficult to verify. This paper introduces Credo, which represents semantic state as beliefs and regulates behavior using declarative policies defined over these beliefs. This design supports adaptive, auditable, and composable execution through a database-backed semantic control plane. We showcase these concepts in a decision-control scenario, where beliefs and policies declaratively guide critical execution choices (e.g., model selection, retrieval, corrective re-execution), enabling dynamic behavior without requiring any changes to the underlying pipeline code.

Figures & tables

Figure 1. Accuracy vs. cost for each of the 18 configurations on 100 randomly chosen tasks from FinanceBench ( Islam et al., 2023 ) .

Figure 2. Overview of Credo . Developers specify a logical LLM pipeline accompanied by a set of declarative beliefs and policies that form its semantic control plane, allowing adaptivity without directly modifying the underlying code. The observation layer evaluates beliefs based on available evidence, the decision layer evaluates policies over belief values and associated confidence scores, and the execution layer applies the corresponding rewrites before continuing with the updated physical plan.

Figure 4. Credo ’s web interface. \raisebox{-.9pt} {1}⃝ Query Box: Allows selecting from predefined benchmark tasks or submitting a custom query. \raisebox{-.9pt} {2}⃝ Logical Plan: Shows the high-level operators that make up the LLM pipeline. \raisebox{-.9pt} {3}⃝ Belief Catalog: Reports each belief’s current (value, confidence) pair based on the available evidence and allows for the definition of new beliefs. \raisebox{-.9pt} {4}⃝ Policy Catalog: Lists the active policies and supports inline updates, as well as the creation of new policies. \raisebox{-.9pt} {5}⃝ Physical Plan: Displays the operator configurations produced during compilation and highlights subsequent rewrites as policies fire. \raisebox{-.9pt} {6}⃝ Event History: Records a trace of evaluated beliefs, triggered policies, and operator executions, including details like inputs/outputs, cost, and latency.

LLM Agent Orchestration

Large language model agent orchestration coordinates models, tools, and workflows to complete complex tasks reliably and efficiently.

See all 458 papers

LLM-as-Code: Agentic Programming for Agent Harness
Jun 14, 2026Junjia Qi, Zichuan Fu, Jingtong Gao +4AI Agent Reliability LLM Agent Orchestration
City University of Hong Kong · Tencent Jarvis Lab
Decision-Centric Design for LLM Systems
Apr 1, 2026Wei SunLLM Decision-Making Language Model-Based Control
IBM Research
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
Jul 15, 2026Amirhosein Ghasemabadi, Ruichen Chen, Bahador Rashidi +1Multi-Agent LLM Systems Language Model-Based Control
1ECE Department, University of Alberta · 2Huawei Technologies Canada Co., Ltd.

Jun 14, 2026J/K move · Enter open · S save

LLM-as-Code: Agentic Programming for Agent Harness

Junjia Qi, Zichuan Fu, Jingtong Gao, Wenlin Zhang+3

City University of Hong Kong · Tencent Jarvis Lab

AI Agent Reliability LLM Agent Orchestration Long-Horizon LLM Agents LLM Agent Reliability

Open paper AskPDF arXiv

Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, control-flow hallucination, and unreliable completion are not implementation bugs but architectural consequences of assigning the deterministic work of looping, branching, and sequencing to a probabilistic system. A better prompt or a stronger model cannot guarantee the reliability of the LLM agent. We therefore propose Agentic Programming, in which the program governs all control flow, and the LLM is itself part of it, an adaptive component we call LLM-as-Code and invoke only where a task calls for reasoning or generation. Within each call the model keeps full flexibility, but it cannot alter the program's execution path. With control in the program, the LLM's context is built from the execution history's call tree and forms a directed acyclic graph (DAG). Each call's context length is then determined by its call depth rather than by accumulation over steps. A case study of computer-use agents shows that the design is practical, not just a theoretical stance, substantially improving the stability of long visual operation sequences.

Abstract

LLM Agent Orchestration

Explore similar work

LLM-as-Code: Agentic Programming for Agent Harness

Decision-Centric Design for LLM Systems

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making