Governance Decay
PulseAugur coverage of Governance Decay — every cluster mentioning Governance Decay across labs, papers, and developer communities, ranked by signal.
-
AI guardrails can degrade during agent self-summarization, study finds
A new paper explores how AI guardrails can degrade or disappear during the self-summarization process used by long-running AI agents. Researchers found that simply checking for the textual presence of a safety rule is i…
-
AI agent summarization silently loses rules, increasing policy violations
A new benchmark called ConstraintRot, detailed in the paper Governance Decay, reveals that AI agent summarization techniques can silently lose critical rules, leading to increased policy violations. When rules were full…
-
New benchmarks and safety methods emerge for advanced LLM agents
New research explores the development and evaluation of AI agents, focusing on their ability to navigate complex environments and adhere to policies. StarDojo benchmarks agent performance in open-ended simulations like …