Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools

• URL: http://arxiv.org/abs/2608.19888v1
• Date: Thu, 20 Aug 2026 10:54:17 GMT
• Title: Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools
• Abstract summary: Reuse and spawn are posed as one-sided sequential hypotheses on a conditional (mechanism-level) discrepancy.<n>We prove finite-time anytime validity for the observable surrogate discrepancy of a predictable discriminator sequence.<n>On synthetic multi-concept streams, Electricity, Covertype, and the recurrence-heavy INSECTS benchmark, the instance-accounted restarted bank achieves zero false spawns.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one, or defer. We present a decision layer that makes all three outcomes statistically meaningful. Reuse and spawn are posed as one-sided sequential hypotheses on a conditional (mechanism-level) discrepancy, separated by an indifference zone; defer is exactly the state in which neither betting e-process has accumulated sufficient evidence. We prove finite-time anytime validity for the observable surrogate discrepancy of a predictable discriminator sequence, and an unconditional one-sided transfer to the population quantity in which each side's slack is the excess risk of a single discriminator; an empirically observed downward-bias regularity makes the spawn side exactly conservative. Recency without sacrificing the guarantee is obtained by a restarted e-detector: a bank of unwindowed betting supermartingales at geometrically spaced restart times (O(log t) memory), with the error budget spent over restart instances, which preserves lifetime anytime validity; spending over expert-creation order likewise controls multiplicity for unboundedly many experts. On synthetic multi-concept streams, Electricity, Covertype, and the recurrence-heavy INSECTS benchmark, the instance-accounted restarted bank achieves zero false spawns and zero false reuses after switches and matches or exceeds the retired windowed heuristic (INSECTS-reoccurring accuracy 0.675), making the deployed algorithm and the guaranteed algorithm one and the same.

Related papers

• RAPTOR: Role-Aware Private Training for Mixture-of-Experts [68.5626338219096]
  RAPTOR is a Role-Aware Private Training framework.<n>RAPTOR alternates shared and expert optimization and targets each failure directly.<n> Experiments on Switch Transformer and OLMoE fine-tuning across GLUE tasks, and on DeepSeek-VL2-Tiny, show consistent gains over standard DP baselines.
  arXiv  Detail & Related papers  (2026-09-04T23:16:12Z)
• Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents [16.24087700490158]
  Large language model agents are increasingly deployed as autonomous loops.<n>We show that this is a failure of composition rather than an implementation detail.<n>We present LoopHarness, which restores a persistent, non-decaying safety state at the loop level.
  arXiv  Detail & Related papers  (2026-08-27T13:52:31Z)
• SynthGuard-ReleaseBench: Locked-Audit Evidence for Synthetic Tabular Data Releases [0.0]
  We introduce SynthGuard-ReleaseBench, an audit framework that locks the use, candidate panel, tolerances, and audit schedule before evaluation.<n>It compares real-trained and synthetic-trained on protected data, gives simultaneous finite-sample bounds for loss gaps, requires controls, and keeps utility, empirical privacy risk mechanism claims separate.
  arXiv  Detail & Related papers  (2026-08-14T03:12:17Z)
• Simplex Relaxation for Discrete Diffusion [58.33696160279345]
  We introduce Simplax, an exact Dirichlet--categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable.<n>Simplax improves the generative perplexity--entropy tradeoff on unconditional OpenWebText generation.
  arXiv  Detail & Related papers  (2026-08-11T07:58:17Z)
• The Need for an External Observer Formalizing the Sufficiency Gap: A Mathematical Extension of Mixture Identifiability and Contextual Grounding in Sequence Models [0.0]
  We construct a binary mixed-regime process with one deterministic textual regime and one random regime governed by an unobserved latent state.<n>The resulting entropy difference is not an ordinary optimization error; it is a sufficiency gap caused by marginalization over an unobserved state.<n>A corrective signal reverses the posterior odds induced by the textual history exactly when its fidelity exceeds the text-only posterior weight assigned to the misleading regime.
  arXiv  Detail & Related papers  (2026-05-26T08:53:11Z)
• Learning Context-conditioned Gaussian Overbounds for Convolution-Based Uncertainty Propagation [4.891998873486944]
  We propose a unified learning framework that trains neural networks to produce context-aware Gaussian overbounds.<n>We provide a scoped analysis of discrete-to-continuous conservatism and compact-domain objective regularity.<n>The framework is modality-agnostic and applicable to learning systems that require conservative, feature-conditioned uncertainty estimates.
  arXiv  Detail & Related papers  (2026-05-15T09:47:05Z)
• Belief Memory: Agent Memory Under Partial Observability [56.41506249481312]
  We propose BeliefMem, which shifts the memory paradigm from committing to a single conclusion per observation to retaining multiple candidate conclusions with their probabilities.<n> BeliefMem preserves the uncertainty that the deterministic paradigm discards, enabling the agent to act with high confidence.<n> Empirical evaluations on LoCoMo and ALFWorld benchmarks show that, even with limited data, BeliefMem achieves the best average performance.
  arXiv  Detail & Related papers  (2026-05-07T02:03:13Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Core Safety Values for Provably Corrigible Agents [2.6451153531057985]
  We introduce the first implementable framework for corrigibility, with provable guarantees in multi-step, partially observed environments.<n>Our framework replaces a single reward with five *structurally separate* utility heads.<n>For open-ended settings where adversaries can modify the agent, we prove that deciding whether an arbitrary post-hack agent will ever violate corrigibility is undecidable.
  arXiv  Detail & Related papers  (2025-07-28T16:19:25Z)
• Sequential Predictive Two-Sample and Independence Testing [114.4130718687858]
  We study the problems of sequential nonparametric two-sample and independence testing. We build upon the principle of (nonparametric) testing by betting.
  arXiv  Detail & Related papers  (2023-04-29T01:30:33Z)
• Universal Off-Policy Evaluation [64.02853483874334]
  We take the first steps towards a universal off-policy estimator (UnO) We use UnO for estimating and simultaneously bounding the mean, variance, quantiles/median, inter-quantile range, CVaR, and the entire cumulative distribution of returns.
  arXiv  Detail & Related papers  (2021-04-26T18:54:31Z)

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.