# TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory

arXiv: https://arxiv.org/abs/2606.06240 · HTML: https://mlsanity.com/paper/2606.06240/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 38 of its 75 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 30 of 38)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing](https://mlsanity.com/paper/2410.12189/) (2024)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents](https://mlsanity.com/paper/2604.20006/) (2026)
- [Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First](https://mlsanity.com/paper/2509.00997/) (2025)
- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues](https://mlsanity.com/paper/2605.12493/) (2026)
- [Useful Memories Become Faulty When Continuously Updated by LLMs](https://mlsanity.com/paper/2605.12978/) (2026)
- [APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI](https://mlsanity.com/paper/2604.14362/) (2026)
- [Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents](https://mlsanity.com/paper/2604.15877/) (2026)
- [GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations](https://mlsanity.com/paper/2605.14498/) (2026)
- [MemLineage: Lineage-Guided Enforcement for LLM Agent Memory](https://mlsanity.com/paper/2605.14421/) (2026)
- [Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents](https://mlsanity.com/paper/2601.07468/) (2026)
- [FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory](https://mlsanity.com/paper/2601.18642/) (2026)
- [BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents](https://mlsanity.com/paper/2603.23848/) (2026)
- [Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking](https://mlsanity.com/paper/2604.11581/) (2026)
- [Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning](https://mlsanity.com/paper/2602.18493/) (2026)
- [S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination](https://mlsanity.com/paper/2605.17076/) (2026)
- [Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory](https://mlsanity.com/paper/2605.10870/) (2026)
- [Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents](https://mlsanity.com/paper/2604.22085/) (2026)
- [Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory](https://mlsanity.com/paper/2604.11544/) (2026)
- [H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure](https://mlsanity.com/paper/2605.15701/) (2026)
- [ATCC: Adaptive Concurrency Control for Unforeseen Agentic Transactions](https://mlsanity.com/paper/2603.13906/) (2026)
- [Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory](https://mlsanity.com/paper/2604.03588/) (2026)
- [WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation](https://mlsanity.com/paper/2604.18478/) (2026)
- [MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing](https://mlsanity.com/paper/2605.02199/) (2026)

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

- [MemTX: Transactional Belief Commit for Stateful Agent Memory](https://mlsanity.com/paper/2607.23929/) (2026)
- [PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents](https://mlsanity.com/paper/2606.12329/) (2026)
- [LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation](https://mlsanity.com/paper/2608.12990/) (2026)
- [Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems](https://mlsanity.com/paper/2610.08101/) (2026)
- [Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents](https://mlsanity.com/paper/2608.12476/) (2026)
- [Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution](https://mlsanity.com/paper/2609.27417/) (2026)
- [Personalized State-Transition-Aware Memory for Clinical Agents](https://mlsanity.com/paper/2609.38490/) (2026)
- [Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation](https://mlsanity.com/paper/2610.10265/) (2026)

## Abstract (arXiv)

Persistent memory for an LLM agent is a write-heavy substrate: every belief update is a versioned write, and a new claim may contradict a stored one. Production systems use four resolution heuristics (last-writer-wins, evidence-weighted merge, await-confirmation, per-rule policy), yet none declares the isolation level it assumes or the write-time anomalies it admits. We show that contradiction resolution is write-time concurrency control and make the missing contract explicit. TOKI types the four heuristics as one family of bitemporal operators over a dual-row schema, each with an isolation precondition and a provenance annotation that preserves the losing fact in an audit row. Four soundness theorems close the contract across isolation, schema, and provenance, lift the guarantees to operator pipelines, and extend the fold operators to n-ary conflict sets. A tightness companion proves that, within the relational schedule model, keyed logging of the adjudicating judge is necessary for replay consistency, which every audited baseline omits. A verdict matrix over eight systems localizes the gap: every baseline that keeps a language-model judge on the write path admits at least one of three write-time anomalies (replay inconsistency, belief-drift skew, audit erasure); a content-addressed engine-layer comparator avoids them only by removing the judge, and TOKI alone excludes all three while keeping it. On its one natural-workload slice the audit-row defence moves LoCoMo by 0.86, and ablating the typed memory layer removes 0.49 accuracy on 1,444 answerable LoCoMo questions; the cross-system comparison stays underpowered and claims no superiority. The contribution is the contract: a write-time correctness specification, proved sound across isolation, schema, and provenance, pinning the guarantee every production heuristic assumes but no deployed system makes explicit.