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

• URL: http://arxiv.org/abs/2605.19576v1
• Date: Tue, 19 May 2026 09:19:56 GMT
• Title: Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
• Abstract summary: Self-evolving skill libraries face a silent failure mode we term emphlibrary drift: skill accumulation without outcome-driven lifecycle management causes retrieval degradation, false-positive injections, and performance stagnation.<n>Recent evaluation confirms the symptom--LLM-authored skills deliver +0.0pp gain while human-curated ones deliver +16.2pp (Bench)
• Score: 9.989306175511238
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-evolving skill libraries face a silent failure mode we term \emph{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.

Related papers

• Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery [7.414694666903067]
  GuardrailLoop is a simulation-based testbed that makes three operational contracts jointly testable.<n>A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions.<n>It separates useful adaptation, state recovery, and repeated execution.
  arXiv  Detail & Related papers  (2026-09-10T21:22:08Z)
• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents [0.0]
  We present an agent instrument built so that verification is structural rather than post-hoc.<n>Every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached.<n>We report a clean, single-variable result on a failure every long-horizon agent suffers.
  arXiv  Detail & Related papers  (2026-08-04T15:10:37Z)
• AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows [1.6785141970297952]
  AEVAL (Agentic Evaluation) is a CI-integrated framework that replaces this practice with a deterministic, reproducible test pipeline for agentic skills.<n>Every skill change triggers a test event: the skill runs against a developer declared evaluation contract inside an automated executor.<n>A key ingredient is a structural separation between executor and grader, preventing a subtle but pervasive failure mode.
  arXiv  Detail & Related papers  (2026-07-16T21:33:05Z)
• Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents [9.989306175511238]
  We introduce textbfRatchet, a single-agent loop in which a frozen LLM writes, retrieves, curates, and retires its own natural-language skills.<n>Ratchet integrates four candidate hygiene mechanisms: outcome-driven retirement, a bounded active-cap, meta-skill authoring guidance, and pattern canonicalisation.
  arXiv  Detail & Related papers  (2026-05-21T08:20:38Z)
• ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation [0.0]
  This report presents a tool-augmented autonomous reasoning framework built around planner-directed execution, specialized tool use, and telemetry-driven evaluation.<n>We analyze ChromaFlow on GAIA 2023 Level-1 validation tasks under clean evaluation constraints.
  arXiv  Detail & Related papers  (2026-05-13T20:40:37Z)
• Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries [14.848157882117613]
  LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and they reference evolve.<n>We formulate skill drift as contract violation and introduce sgname, which extracts executable environment contracts from skill documents.<n>sgname raises zero false alarms over 599 no-drift and hard-negative cases.
  arXiv  Detail & Related papers  (2026-05-09T11:41:53Z)
• Beyond Completion: Probing Cumulative State Tracking to Predict LLM Agent Performance [9.771590610969918]
  We introduce Working Memory Fidelity-Active Manipulation (WMF-AM)<n>We evaluate it on 20 open-weight models (0.5B-35B, 13 families) against a released deterministic 10-task agent battery.
  arXiv  Detail & Related papers  (2026-03-28T17:25:11Z)
• First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution [0.0]
  First-mover bias is a concentration of feature importance caused by sequential residual fitting in gradient boosting.<n>We show that model independence is sufficient to resolve first-mover bias in the linear regime, and remains the most effective mitigation under nonlinear data-generating processes.
  arXiv  Detail & Related papers  (2026-03-22T02:59:40Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework [1.9180507495574395]
  Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains.<n>Existing explainability methods either provide only local insights (SHAP, LIME) or employ oversimplified surrogates failing to capture continuous dynamics.<n>This work proposes a Fuzzy System (FCS) distilling neural policies into human-readable IF-THEN rules through K-Means clustering for state-readable partitioning.<n>Three quantifiable metrics are introduced: Rule Density (FRAD) measuring explanation focus, Fuzzy Set Coverage (FSC) validating vocabulary completeness, and Action Space Granularity (
  arXiv  Detail & Related papers  (2026-02-24T23:53:01Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral [59.14787085809595]
  We identify Lazy Likelihood Displacement (LLD) as the core mechanism driving this failure.<n>LLD emerges early and triggers a self-reinforcing LLD Death Spiral, where declining likelihood leads to low-confidence responses.<n>We propose a lightweight likelihood-preserving regularization LLDS for GRPO that activates only when a trajectory's likelihood decreases.
  arXiv  Detail & Related papers  (2025-12-03T19:41:15Z)
• SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents [52.20768003832476]
  We analyze execution traces on $$-Bench (Airline/Retail) and SWE-Bench Verified.<n>We formalize emphdecisive deviations, earliest action, level divergences that flip success to failure.<n>We introduce cm, a model-agnostic, gradient-free, test-time safeguard.
  arXiv  Detail & Related papers  (2025-11-26T01:28:22Z)
• LLMs Can Get "Brain Rot"! [68.08198331505695]
  Continual exposure to junk web text induces lasting cognitive decline in large language models (LLMs)<n>We run controlled experiments on real Twitter/X corpora, constructing junk and reversely controlled datasets.<n>Results provide significant, multi-perspective evidence that data quality is a causal driver of LLM capability decay.
  arXiv  Detail & Related papers  (2025-10-15T13:28:49Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.