mlsanityData to 14 Oct 2026

Correct Is Not Governed: Provenance Integrity in Agentic Workflows

arXiv 2608.12761 ↗First posted 13 Aug 2026cs.AI cs.CRcited by 2

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the wrong authority, an unsupported completion claim, or work made stale by a later change. We define governed execution as work whose decisions, completion, and response to change are supported by inspectable provenance. We present Matrix, a deterministic causal-state layer that records authority and fact dependencies, verifies completion evidence, and selectively invalidates affected work. Across controlled comparisons, governed and direct workflows often reached the same outcomes, but only the governed path consistently preserved governing evidence, refused unsupported closure, and limited recovery to dependent tasks. A role-separated transfer challenge then failed: a deterministically enforced completeness contract severely over-blocked synthetic packets produced outside its authoring context. These results do not establish Matrix as a general accuracy enhancer; they support its primary role as an institutional integrity layer for making agentic work auditable and independently verifiable.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 11 of its 27 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

11 of 27 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026Auditing Provenance Sensitivity in LLM Agent Action Selection23 Jul
  2. 2026Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents11 Jul
  3. 2026Safeguarding LLM Agents from Misalignment through Provenance Analysis1 May
  4. 2026Runtime Governance for AI Agents: Policies on Paths17 Mar
  5. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents24 Mar

Other references · 6

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  3. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  4. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Taskscited by 142
  5. 2026ToolGate: Contract-Grounded and Verified Tool Execution for LLMscited by 15
  6. 2026From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Workcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
  2. 2026Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows
  3. 2026REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows
  4. 2026MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
  5. 2026From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering
  6. 2026Responsible Agentic AI Requires Explicit Provenance
  7. 2026Structure Before Intelligence: Gating What Agentic Scientific Workflows Release
  8. 2026Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows