# ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control arXiv: https://arxiv.org/abs/2607.22962 ยท HTML: https://mlsanity.com/paper/2607.22962/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 24 of its 28 references that are in the map. - First posted on arXiv 25 Jul 2026. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/) ## Builds on (most cited first, 24 of 24) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020) - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (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) - [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023) - [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023) - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023) - [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022) - [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022) - [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023) - [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021) - [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023) - [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023) - [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020) - [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023) - [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024) - [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023) - [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023) - [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022) - [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021) - [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024) - [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023) - [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023) - [Adaptive Memory Admission Control for LLM Agents](https://mlsanity.com/paper/2603.04549/) (2026) ## Built on by (most cited first, 6 of 6) - [Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents](https://mlsanity.com/paper/2609.02127/) (2026) - [A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory](https://mlsanity.com/paper/2609.30813/) (2026) - [Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures](https://mlsanity.com/paper/2609.25052/) (2026) - [Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents](https://mlsanity.com/paper/2609.36130/) (2026) - [EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment](https://mlsanity.com/paper/2609.38661/) (2026) - [AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory](https://mlsanity.com/paper/2610.07707/) (2026) ## Abstract (arXiv) LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning. A hallucinated fact written at one step therefore persists as a false premise for every subsequent step, a failure mode we call memory contamination. Existing memory management addresses retrieval and capacity but not write-time correctness; this admission problem cannot be solved by utility- or recency-based criteria, and uncontrolled contamination compounds across long trajectories. We propose ConsistencyGate, a write-time admission gate that, before committing a candidate fact m extracted from context c, queries the LLM K times for a soft support score and admits m only when the average exceeds a threshold. The mechanism is model-agnostic, requires no fine-tuning, and reduces to a single forward pass in a log-probability variant for latency-sensitive deployments. To measure the effect on natural data, we construct two real-conversation benchmarks (LoCoMo-Contam and MSC-Contam) by planting controlled single-detail corruptions in long-term conversations from LoCoMo and MSC, and complement them with a structured synthetic corpus (MemContam) that isolates a near-oracle upper bound. Across four LLM backbones, ConsistencyGate reduces contamination on every benchmark relative to a write-everything baseline, with the cost concentrated on facts that are stated only implicitly in the source context. We release all three benchmarks together with the gate implementation.