Silent Collapse in Recursive Learning Systems

• URL: http://arxiv.org/abs/2605.14588v2
• Date: Tue, 19 May 2026 14:15:06 GMT
• Title: Silent Collapse in Recursive Learning Systems
• Abstract summary: We propose a lightweight metacognitive loop that monitors trajectory statistics and estimates a slow-timescale trust variable.<n>MTR provides early warning and actively prevents silent collapse without requiring access to pristine real data.
• Score: 24.578102943388256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics (loss, perplexity, accuracy) often fail to detect internal degradation before it becomes irreversible. Here we identify a phenomenon we call silent collapse: under broad recursive conditions, model internal distributions -- predictive entropy, representational diversity, and tail coverage -- progressively contract even as conventional metrics appear stable or improving. We discover that silent collapse is not abrupt. Its onset is reliably preceded by three trajectory-level precursors: (1) contraction of anchor entropy, (2) freezing of representation drift, and (3) erosion of tail coverage. These signals manifest multiple generations before any degradation in standard validation metrics, enabling early warning. Based on these precursors, we propose the MTR (Monitor--Trust--Regulator) framework, a lightweight metacognitive loop that monitors trajectory statistics, estimates a slow-timescale trust variable, and adaptively modulates the effective learning intensity. MTR provides early warning and actively prevents silent collapse without requiring access to pristine real data -- a critical advantage when original data is unavailable, contaminated, or private.

Related papers

• Evidence of Absence: Cross-Modal Abductive Risk Perception to Sustain World Models When Vision Fails [11.206758778146282]
  A structured world-state is designed to preserve prediction-critical content when perception degrades, but it presumes observations to populate it.<n>We address how to sustain the world model from a complementary modality by treating the absence of expected co-evidence as evidence of a hidden cause.<n>A microphone-array front-end estimates the bearing of engine and tire sources and extracts approach-rate evidence.
  arXiv  Detail & Related papers  (2026-08-15T00:38:17Z)
• Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness [0.16921396880325779]
  We test whether activation monitors trained on a base model remain reliable after routine model updates.<n>We find a sharp split: quantization-style updates largely preserve frozen probe performance, while fine-tuning-style updates frequently make probes stale.<n>We also show that degradation is predictable from pre-deployment features, enabling revalidation budgets to be triaged toward the monitors most likely to fail.
  arXiv  Detail & Related papers  (2026-06-14T19:07:22Z)
• Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction [1.0981335059631014]
  We identify a critical perception-dynamics gap in existing anomaly signals.<n>We propose an Anomaly-Informed Online approach that fuses two anomaly scores extracted from a world model.
  arXiv  Detail & Related papers  (2026-05-20T12:43:09Z)
• Learning Uncertainty from Sequential Internal Dispersion in Large Language Models [52.29267172760918]
  Uncertainty estimation is a promising approach to detect hallucinations in large language models.<n>Recent approaches commonly depend on model internal states to estimate uncertainty.<n>We present Sequential Internal Variance Representation (SIVR), a supervised hallucination detection framework.
  arXiv  Detail & Related papers  (2026-04-17T06:31:29Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models [7.400285974510125]
  We introduce transplantation activation, a causal intervention that manipulates hidden states by imposing the statistical moments of one event onto another.<n>We find that models encode a graded notion of event severity, with the latent vector norm directly correlating with the magnitude of systemic shocks.<n>Our findings provide evidence for a latent concept space that governs model predictions, shifting interpretability from post-hoc attribution to direct causal intervention.
  arXiv  Detail & Related papers  (2025-09-06T18:28:20Z)
• METANOIA: A Lifelong Intrusion Detection and Investigation System for Mitigating Concept Drift [6.988127333802916]
  We present METANOIA, the first lifelong detection system that mitigates the high false positives due to concept drift.<n>Using state-of-the-art benchmarks, we demonstrate that METANOIA improves precision performance at the window-level, graph-level, and node-level by 30%, 54%, and 29%, respectively.
  arXiv  Detail & Related papers  (2024-12-31T13:44:27Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)

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.