arXiv AI
Jun 6
Data Flow Control: Data Safety Policies for AI Agents
arXiv:2606. 05679v1 Announce Type: cross Abstract: Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users.
Credo: Declarative Control of LLM Pipelines via Beliefs and Policies
arXiv:2604. 14401v2 Announce Type: replace Abstract: Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions.
Related stories
arXiv AI
2d ago
Sapien: A Stateful Policy Engine for Autonomous AI Agents
Sapien is a policy engine that enforces stateful contextual policies for autonomous AI agents, specifying allowed tool‑call sequences with an extended regular expression that includes stateful predicates, deferred policy generation, and scoped semantic checks. The system maintains performance close to an unconstrained agent while significantly reducing malicious actions, ruling out 93‑95% of attacks on AgentDojo and 62‑85% on Toolathlon, outperforming traditional tool allowlists on long‑horizon tasks.
Hugging Face Trending Papers
Jun 4
Data Flow Control: Data Safety Policies for AI Agents
Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users. While recent work improves query correctness, correctness is not safety.
arXiv AI
Aug 18
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.
arXiv AI
4d ago
Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety
arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/...
arXiv AI
Aug 11
Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy
arXiv:2608. 09857v1 Announce Type: cross Abstract: Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on execution rather than verifying the feasibility actions planning models propose.
arXiv AI
Aug 26
Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications
Granite.Trust Policy Tools introduces a YAML-based Actionable Policy schema that specifies what content a generative AI model can or cannot produce, allowing exception-based governance. It also offers a synthetic data generation pipeline to create policy-aligned training data and a suite of tools for defining and enforcing these policies throughout the AI lifecycle. The tools and example policies are open source, enabling organizations to tailor safety policies to their specific risks and regulatory contexts.
arXiv AI
Sep 2
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
The paper introduces control‑data flow separation to improve prompt optimization in multi‑agent large language model systems. By representing execution protocols as typed, validated program objects and keeping task‑relevant content as unstructured language, the method prevents prompt edits from corrupting critical routing, formatting, or termination signals. Experiments on synthetic reasoning, collaborative review generation, and insurance rating workflows show that this approach maintains 100% protocol validity while consistently enhancing task performance.
arXiv AI
Jul 1
Containment Verification: AI Safety Guarantees Independent of Alignment
arXiv:2605. 09045v2 Announce Type: replace Abstract: Agentic frameworks are the software layer through which AI agents act in the world.
Hugging Face Trending Papers
Jun 25
A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO
We introduce the process harness, a new mechanism for uplifting legacy workflows into Agentic Business Process Management (Agentic BPM) without replacing the underlying workflow engine. A process harness places a policy-governed agentic layer around a deterministic workflow engine, intercepting designated control points to contribute reasoning, adaptation, and oversight while the engine retains structural authority over the process.
arXiv AI
Aug 17
Agentic Transaction: Towards ACID-Compliant Agent Systems
arXiv:2608. 13900v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasoning, tool use, code generation, and workspace manipulation.
arXiv AI
Jul 21
Composable Verification Pipelines for Multi-Agent Systems
arXiv:2607. 16266v1 Announce Type: cross Abstract: Existing approaches for reasoning about action and change provide expressive semantics for modeling dynamic systems, in most cases built on top of logic programming systems.