MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Artificial Intelligence
Title:MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
Abstract:Persistent memory lets long-running large language model agents reuse information across sessions and tasks. Yet errors in writable memory can persist and corrupt future behavior. Existing systems improve storage and retrieval, but they do not provide a transaction boundary for reliable updates and recovery. We therefore propose MemTxn, a governance layer outside the answer model. MemTxn verifies whether an update is supported by its source. It also selects the visible version when facts conflict and restores the application-visible state after a fault. The system uses Ordered PatchTest to validate writes, a Temporal Resolver to select versions, and a durable snapshot journal to recover state. On an item-disjoint audit, MemTxn accepts all 60 supported originals and rejects all 179 hard negatives. Under persistent multi-key faults on LongMemEval-S and LoCoMo states, it restores the complete declared active map without knowing the actual physical write set. On MemoryAgentBench FactConsolidation, MemTxn achieves the highest average F1 across all twelve answer-model configurations. It outperforms Dense by 17.06--24.07 points in five representative settings.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.27834 [cs.AI] |
| (or arXiv:2607.27834v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.27834
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — NLP / Computation & Language
-
Procedural Fairness Failures in RLHF from Preference Averaging
Aug 12
-
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Aug 12
-
Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation
Aug 12
-
Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents
Aug 12
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.