{"slug": "the-blind-curator-how-a-biased-judge-silently-disables-skill-retirement-in-self", "title": "The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents", "summary": "Researchers at arXiv show that biased LLM judges silently disable skill retirement in self-evolving agents, causing a mechanism failure that no amount of data can fix. The study reveals that false-pass bias, where failures are incorrectly rated as passes, prevents agents from retiring bad skills beyond a sharp threshold. A cheap defect-injection audit can detect this failure before deployment.", "body_md": "arXiv:2607.07436v1 Announce Type: new\nAbstract: A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps a growing library from drifting below the no-skill baseline, but its guarantee assumes an unbiased reward, which is false for the LLM judges that reference-free tasks force upon us. We show that a biased judge does not merely add noise; it \\emph{silently switches off the curator}. We make this precise with a corrupted-reward analysis and, isolating the causal channel by injecting corruption on top of a deterministic reward, a behavioral study on a reference-free report-writing testbed with a code-generation cross-check. Symmetric noise leaves retirement intact, but \\emph{false-pass} bias (failures slipping through as passes) disables contribution-based retirement past a sharp threshold that no amount of data can cross. Separating genuine retirement from cap-eviction churn shows this \\emph{mechanism} failure is universal, holding across domains and failure rates and sparing only near-zero-false-pass, verifier-like graders. The downstream \\emph{outcome}, though, is regime-dependent: eval quality degrades only where the same corruption also starves skill synthesis, and otherwise holds steady, so the disabled curator is \\emph{silent}, surfacing in no aggregate metric. The contribution is a behavioral safety result, not a performance one. A cheap defect-injection audit then tells an operator, before deployment, which side of the threshold their judge occupies.", "url": "https://wpnews.pro/news/the-blind-curator-how-a-biased-judge-silently-disables-skill-retirement-in-self", "canonical_source": "https://www.machinebrief.com/news/the-blind-curator-how-a-biased-judge-silently-disables-skill-f4vk", "published_at": "2026-07-09 04:00:00+00:00", "updated_at": "2026-07-09 05:25:12.312826+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-safety", "ai-agents", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/the-blind-curator-how-a-biased-judge-silently-disables-skill-retirement-in-self", "markdown": "https://wpnews.pro/news/the-blind-curator-how-a-biased-judge-silently-disables-skill-retirement-in-self.md", "text": "https://wpnews.pro/news/the-blind-curator-how-a-biased-judge-silently-disables-skill-retirement-in-self.txt", "jsonld": "https://wpnews.pro/news/the-blind-curator-how-a-biased-judge-silently-disables-skill-retirement-in-self.jsonld"}}