AIBearisharXiv – CS AI · 8h ago7/10
🧠
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
Researchers discover that LLM agents lose safety compliance when governance constraints are compressed or summarized during long sessions, with violations rising from 0% to 59% after context compaction. The study introduces a benchmark demonstrating this 'Governance Decay' failure mode and proposes Constraint Pinning as a training-free mitigation.