SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
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 \textbf{reproducible trigger}: ablations that isolate drift: one disables skill injection (flat floor, +0.002), one imposes premature retirement (active harm, $-$0.019); (2) \textbf{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 \textbf{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.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM agent systems accumulate disorder leading to silent failures, formalized by the exponential Entropy Principle S(t) = S0 * e^(alpha * t) with empirically measured alpha, countered by proposed PIG Engine and ADE protocols.
citing papers explorer
-
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
-
Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agents
LLM agent systems accumulate disorder leading to silent failures, formalized by the exponential Entropy Principle S(t) = S0 * e^(alpha * t) with empirically measured alpha, countered by proposed PIG Engine and ADE protocols.