Stored as Fact, Obeyed as Instruction: Cross-Session Memory Poisoning and the Write-Governance Gap in LLM Agents

Long-term memory gives a large language model (LLM) agent continuity across sessions, and it gives an attacker persistence: content written once is retrieved later as the agent's own note. This study measures cross-session memory poisoning and seven memory write-governance policies in a local laboratory. A synthetic corpus of 48 poison instances in six classes and 24 benign instances was planted through tool, document, and user channels, and a local model, Qwen2.5-3B-Instruct, was probed in later sessions with each memory present and in paired no-memory controls. With no gate in place, one stored write influenced the later session in 0.708 of cases (34 of 48; Wilson 95% CI [0.568, 0.818]) against a control rate of 0.021, and the effect did not decay by session 4. Provenance gating and a review queue each cut influence to 0.229, although provenance left user-channel poison at the ungated rate of 0.833, while review rejected 0.458 of benign memories. Type separation converted surviving poison into false facts at full strength (0.833 under the policy against 0.833 without it, on tool and document channels). A combined tiered policy matched type separation at distance 1 (0.333) and fell to 0.167 by session 4 on the distance subset, at a benign rejection rate of 0.333. A validation subset on Llama-3.2-1B-Instruct reproduced the policy ordering and the class asymmetry. The measurements support treating every memory write as a provisioning decision governed at the write gate.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-16
DOI
https://doi.org/10.5281/zenodo.24287335
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Stored as Fact, Obeyed as Instruction: Cross-Session Memory Poisoning and the Write-Governance Gap in LLM Agents

Prabin Shrestha
Zenodo (CERN European Organization for Nuclear Research)
Adversarial Robustness in Machine Learning
preprint

Stored as Fact, Obeyed as Instruction: Cross-Session Memory Poisoning and the Write-Governance Gap in LLM Agents

Prabin Shrestha
preprint en

Abstract

Long-term memory gives a large language model (LLM) agent continuity across sessions, and it gives an attacker persistence: content written once is retrieved later as the agent's own note. This study measures cross-session memory poisoning and seven memory write-governance policies in a local laboratory. A synthetic corpus of 48 poison instances in six classes and 24 benign instances was planted through tool, document, and user channels, and a local model, Qwen2.5-3B-Instruct, was probed in later sessions with each memory present and in paired no-memory controls. With no gate in place, one stored write influenced the later session in 0.708 of cases (34 of 48; Wilson 95% CI [0.568, 0.818]) against a control rate of 0.021, and the effect did not decay by session 4. Provenance gating and a review queue each cut influence to 0.229, although provenance left user-channel poison at the ungated rate of 0.833, while review rejected 0.458 of benign memories. Type separation converted surviving poison into false facts at full strength (0.833 under the policy against 0.833 without it, on tool and document channels). A combined tiered policy matched type separation at distance 1 (0.333) and fell to 0.167 by session 4 on the distance subset, at a benign rejection rate of 0.333. A validation subset on Llama-3.2-1B-Instruct reproduced the policy ordering and the class asymmetry. The measurements support treating every memory write as a provisioning decision governed at the write gate.

Zenodo (CERN European Organization for Nuclear Research)
University of the Cumberlands (US)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon