# Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

arXiv: https://arxiv.org/abs/2605.19576 · HTML: https://mlsanity.com/paper/2605.19576/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Self-evolving LLM agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 19 May 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle](https://mlsanity.com/paper/2510.16079/) (2025)
- [AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution](https://mlsanity.com/paper/2603.01145/) (2026)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents](https://mlsanity.com/paper/2604.15877/) (2026)
- [From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution](https://mlsanity.com/paper/2604.15097/) (2026)

## Built on by (most cited first, 10 of 10)

- [SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories](https://mlsanity.com/paper/2606.01311/) (2026)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?](https://mlsanity.com/paper/2605.22148/) (2026)
- [Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents](https://mlsanity.com/paper/2607.12790/) (2026)
- [Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agents](https://mlsanity.com/paper/2606.08162/) (2026)
- [The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents](https://mlsanity.com/paper/2607.07436/) (2026)
- [SCOPE: Score-Isolated Agentic Optimization for Video World Models](https://mlsanity.com/paper/2608.15043/) (2026)
- [Repo2Skill-Evo: Repository Skills Go Stale in Silence](https://mlsanity.com/paper/2608.21964/) (2026)
- [R2 Flow: Recursive Self-Improvement via Recursive Skill Evolution](https://mlsanity.com/paper/2609.33867/) (2026)
- [EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning](https://mlsanity.com/paper/2609.35290/) (2026)

## Abstract (arXiv)

Self-evolving skill libraries face a silent failure mode we term library drift: unbounded skill accumulation without outcome-driven lifecycle management causes retrieval degradation, false-positive injections, and performance stagnation. Recent evaluation confirms the symptom (LLM-authored skills deliver +0.0pp gain while human-curated ones deliver +16.2pp (SkillsBench)), yet the underlying mechanism has not been isolated. We provide (1) a reproducible trigger: ablations that isolate drift: one disables skill injection (flat floor, +0.002), one imposes premature retirement (active harm, -0.019); (2) trace-level diagnostics: an append-only evidence log with per-skill contribution scores, attribution verdicts, and router engagement metrics that make the failure visible before it reaches end-task scores; and (3) a verified fix: a minimal governance recipe (outcome-driven retirement + bounded active-cap + meta-skill authoring prior) that lifts held-out pass@1 from a 0.258 baseline to a late-window mean of 0.584 (rolling gain +0.328) on MBPP+ hard-100 over 100 rounds. Eight ablations decompose which governance mechanisms are load-bearing and which are subsumed, providing a concrete playbook for diagnosing library drift in any self-evolving agent.