Data Flow Control: Data Safety Policies for AI Agents

2026-06-04 · Charlie Summers, Eugene Wu arxiv

Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users. While recent work improves query correctness, correctness is not safety. A query may be semantically valid yet violate regulatory, privacy, or business constraints that govern how data may be combined and released. We argue that enforcing such constraints is fundamentally a data infrastructure problem. This paper introduces Data Flow Control (DFC), a framework to declaratively specify and guarantee policy enforcement over tuple-level data flows within a DBMS query. A key challenge is defining a policy language that is optimizer-invariant yet efficient to enforce at scale. We formalize data safety as aggregate predicates over provenance monomials and present Passant, a portable query rewriting layer that enforces DFC policies without materializing provenance. Across five DBMS engines -- DuckDB, Umbra, PostgreSQL, DataFusion, and SQLServer -- Passant achieves ~0% overhead and outperforms alternatives by orders of magnitude. As a result, Data Flow Control is the first step towards moving data safety from prompts and post-hoc checks into the data infrastructure. Data Flow Control is available open source at https://github.com/dataflowcontrol/data-flow-control.

📄 PDF Abstract BibTeX arXiv:2606.05679

Code (0)

등록된 구현이 없습니다.

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

2026-03-16 · Mumuksh Tayal, Manan Tayal, Ravi Prakash arxiv

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inferen…

Reinforcement Learning Offline RL

Safe Connectivity Maintenance of Underactuated Multi-Agent Networks in Dynamic Oceanic Environments

2023-07-04 · Nicolas Hoischen, Marius Wiggert, Claire J. Tomlin

Autonomous multi-agent systems are increasingly being deployed in environments where winds and ocean currents have a significant influence. Recent work has developed control policies for single agents that leverage flows…

Towards Safe Imitation Learning via Potential Field-Guided Flow Matching

2025-08-12 · Haoran Ding, Anqing Duan, Zezhou Sun, Leonel Rozo 외 arxiv

Deep generative models, particularly diffusion and flow matching models, have recently shown remarkable potential in learning complex policies through imitation learning. However, the safety of generated motions remains …

Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning

2026-02-08 · Manan Tayal, Mumuksh Tayal arxiv

Offline reinforcement learning (RL) provides a compelling paradigm for training autonomous systems without the risks of online exploration, particularly in safety-critical domains. However, jointly achieving strong safet…

Reinforcement Learning Offline RL

Constrained Reinforcement Learning for Predictive Control in Real-Time Stochastic Dynamic Optimal Power Flow

2023-02-21 · Tong Wu, Anna Scaglione, Daniel Arnold

Deep Reinforcement Learning (DRL) has become a popular method for solving control problems in power systems. Conventional DRL encourages the agent to explore various policies encoded in a neural network (NN) with the goa…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)