mlsanityData to 7 Oct 2026

MemTX: Transactional Belief Commit for Stateful Agent Memory

arXiv 2607.23929 ↗First posted 27 Jul 2026cs.AIcited by 12

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current agent memory systems treat every accepted write as immediately actionable truth, so a polluted tool result, a stale update, or a teammate's half-finished note can silently drive an irreversible action. We argue that a memory write is not a belief commit. We present MemTX, a transactional belief-commit protocol. Each record carries evidence, permissions, provenance, and validity. Writes are staged inside snapshot-isolated transactions and admitted by a validate-and-commit pipeline, irreversible tool calls are gated on in-flight belief state, and retracting a belief triggers typed cascading repair of its derived records and tool side effects. Two invariants, action-safety gating and cascade-repair completeness, are machine-checked by property-based testing and bounded exhaustive enumeration of 5.5 million protocol states, with zero violations. Across five backbones from three model families, MemTX leads all eight baselines with paired-McNemar significance on four backbones and statistically ties the best baseline on the fifth and strongest, while remaining the only method with zero downstream harm on every backbone. Backbone capability does not substitute for commit discipline.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 32 of its 39 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

32 of 39 references.

Closest ancestors · 14

Same direction, newest first

  1. 2026Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge25 Jun
  2. 2026Governed Shared Memory for Multi-Agent LLM Systems23 Jun
  3. 2026GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents17 Jun
  4. 2026TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory4 Jun
  5. 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?7 May
  6. 2026WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation20 Apr
  7. 2026Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead9 Mar
  8. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers8 Mar
  9. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents14 Jan
  10. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control23 May
  11. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  12. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
2 more
  1. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  2. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 18

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2024Qwen2.5 Technical Reportcited by 4,713
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  5. 2025OpenAI GPT-5 System Cardcited by 910
  6. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  7. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  8. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 446
  9. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  10. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  11. 2025SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systemscited by 23
  12. 2026From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agentscited by 23
6 more
  1. 2026A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecyclecited by 21
  2. 2026Cordon: Semantic Transactions for Tool-Using LLM Agentscited by 19
  3. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoningcited by 14
  4. 2025TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphscited by 12
  5. 2026Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systemscited by 5
  6. 2026Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memorycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
  2. 2026MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
  3. 2026MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
  4. 2026Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
  5. 2026MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance
  6. 2026Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
  7. 2026The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents
  8. 2026Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents