# Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows

arXiv: https://arxiv.org/abs/2607.00269 · HTML: https://mlsanity.com/paper/2607.00269/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 37 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 9 of 9)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning](https://mlsanity.com/paper/2503.11951/) (2025)
- [Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers](https://mlsanity.com/paper/2606.04421/) (2026)

## Built on by (most cited first, 8 of 8)

- [Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems](https://mlsanity.com/paper/2609.16313/) (2026)
- [The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums](https://mlsanity.com/paper/2609.02925/) (2026)
- [When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority](https://mlsanity.com/paper/2609.20261/) (2026)
- [Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair](https://mlsanity.com/paper/2607.24604/) (2026)
- [From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents](https://mlsanity.com/paper/2609.08015/) (2026)
- [TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views](https://mlsanity.com/paper/2607.21910/) (2026)
- [HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution](https://mlsanity.com/paper/2607.27636/) (2026)
- [Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs](https://mlsanity.com/paper/2609.38266/) (2026)

## Abstract (arXiv)

LLMs increasingly generate workflow actions and repairs that may be well formed yet stale, infeasible, conflicting, or destructive of their own evidence. We introduce Agentic Transaction Processing (ATP), which treats generated actions as untrusted proposals until deterministic admission accepts them under an executable constraint set C. Its two-sided principle is: a proposal is not truth, and no proposal foresees every disruption. Anything may propose, but only the runtime admits and commits; unforeseen disruptions trigger bounded reactive repair whose output re-enters admission. Mnemosyne realizes ATP with an append-only transition log, effective-state projection, dependency-safe compensation, and active contract records. Under stated assumptions and relative to C, we prove four safety properties (authority separation, serial-equivalent generative admission, evidence-preserving repair, and obligation containment) and establish bounded reactive repair. Across nine safety benchmarks and a four-case Temporal SDK comparison, ATP rejects every targeted violation while admitting valid work. A matched data-size sweep measures 5.2-6.6% incremental throughput cost over the same local durable commit path and exposes local saturation. In a companion scheduling harness, local repair edits nearly an order of magnitude fewer operations than global recompute; a 12-scenario interruption stress test rejects every stale recovery candidate without losing observations or producing invalid commits. Two bounded pilots route 80 proposals from four heterogeneous LLMs through the same gate with zero invalid commits; 24 of 40 mid-execution proposals are admitted and 16 are rejected, including four explicit safety rejections.