AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.Recent work shows that dropping a standing safety constraint during compaction drives behavioral violations acrossmany models (Governance Decay; Chen, 2026). We ask a finer question: under a single compaction cycle, how is a safetyrule lost, and what does that imply for detection and evaluation? Our central finding is that a presence check is not asafety check: when compaction does not
Record details
Published: 11 August 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Agents & autonomy
Retrieved: 13 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
arXiv cs.CY · 14 August 2026
MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents
arXiv · 7 August 2026
When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
HuggingFace Daily Papers · 4 August 2026
Inference-Time Policy Alignment for Fair Reinforcement Learning
arXiv fairness query · 31 July 2026
ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
arXiv · 31 July 2026
Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI
arXiv cs.CY · 28 July 2026
How to cite this record
ethics.ai (11 August 2026), “AI Guardrail Survival under Single-Cycle Agentic Self-Summarization,” evidence record 18807, https://ethics.ai/record/18807 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.