# When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority

arXiv: https://arxiv.org/abs/2609.20261 · HTML: https://mlsanity.com/paper/2609.20261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 38 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning](https://mlsanity.com/paper/2503.11951/) (2025)
- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents](https://mlsanity.com/paper/2607.10487/) (2026)
- [S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination](https://mlsanity.com/paper/2605.17076/) (2026)
- [Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows](https://mlsanity.com/paper/2607.00269/) (2026)
- [CoAgent: Concurrency Control for Multi-Agent Systems](https://mlsanity.com/paper/2606.15376/) (2026)
- [ATCC: Adaptive Concurrency Control for Unforeseen Agentic Transactions](https://mlsanity.com/paper/2603.13906/) (2026)
- [Replicating Belief, Not Bits: Epistemic State Replication for Agentic Systems](https://mlsanity.com/paper/2607.09748/) (2026)

## Built on by (most cited first, 2 of 2)

- [The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums](https://mlsanity.com/paper/2609.02925/) (2026)
- [KedgeFlow: A Programmable Control Plane for Enterprise AI Agents](https://mlsanity.com/paper/2610.14810/) (2026)

## Abstract (arXiv)

Autonomous agents derive concrete mutations from database reads, retrieved evidence, policy, beliefs, and delegated authority. Those inputs may change while reasoning is in progress. Database isolation orders the submitted transaction; agentic transaction processing determines whether a proposal satisfies an executable contract. Neither guarantee establishes a common valid point for the mutation and its derivation inputs unless the contract represents the relevant predicates. Typed dependency tokens distinguish content integrity from applicability, and trusted mediation captures the values exposed to reasoning. Under strict Cognitive Serializability, committed effects admit a serial order and a logical event at which every value exposed to derivation is unchanged. The fences last until the runtime event that realizes the sealed durability domain. The weaker Effect-Compatible Cognitive Admission recertifies an effect against a simultaneously held current dependency vector and current policy without claiming to serialize the original stochastic derivation. TCT combines immutable versioned executable definitions, registry-derived authority plans, sealed envelopes, guard-first commit transactions, post-seal envelope- and witness-bound grants, co-committed receipts, idempotent grant finalization, and receipt-driven epistemic reconciliation. Complete registered footprints and a single growing phase induce an acyclic lock-point order over local guards and incompatible external reservations. The corresponding results give serializability conditions and an observational-equivalence boundary for zero-error soundness and positive progress. A falsification suite tests the implementation obligations: the prototype prevented all injected anomalies and added 3.22 ms mean commit overhead.