Intelligent systems reduce redundant work with incremental consistency checks

Incremental Consistency Execution for Autonomous Intelligent Systems

Artificial Intelligence

Summary

Autonomous intelligent systems often use many parts like language models and databases that can change frequently. Re-doing all their work every time something changes wastes a lot of time. The authors propose a method to only redo the parts that really need updating, saving work and speeding things up. Their approach keeps the system’s results consistent and avoids mistakes from stale data.

What this means in practice

Authors

Cheng Li, Jiexiong Liu, Yixuan Chen, Ziheng Huang

Abstract

Long-horizon autonomous intelligent systems rely on heterogeneous components such as large language models, databases, external APIs, and rule engines, while their external states continuously change during execution. Re-executing the entire workflow after every change introduces substantial redundant computation. This paper proposes an incremental consistency execution method based on task fact contracts, field-level dependency masks, and state perturbation result invariant domains. After an initial verified execution, the system constructs conservative invariant domains for critical inputs and uses them to determine whether downstream results can be safely renewed without re-invoking expensive components. When re-execution is required, only the smallest affected output fields are recomputed, and an equivalence barrier prevents unnecessary downstream propagation. A submission-time version consistency gate further ensures the safety of side-effecting actions. Experiments on industrial fault diagnosis, enterprise analytics, and LLM-based multi-tool assistants show that the proposed method significantly reduces expensive component calls and end-to-end latency while maintaining high consistency and low incorrect-reuse rates.