RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments

• URL: http://arxiv.org/abs/2604.18026v1
• Date: Mon, 20 Apr 2026 09:52:36 GMT
• Title: RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
• Abstract summary: We present online tuning as context-conditioned regret minimization.<n>RASP-Tuner instantiates a decomposition motivated by first principles.<n>On nine synthetic non-stationary benchmarks, RASP-Tuner improves or matches cumulative regret relative to our GP-UCB and CMA-ES implementations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many deployed systems expose black-box objectives whose minimizing configuration shifts with an externally observed context. When contexts revisit a small set of latent regimes, an optimizer that discards history pays repeated adaptation cost; when each step must remain inexpensive, full Gaussian-process (GP) refits at high observation counts are difficult to sustain. We cast online tuning as context-conditioned regret minimization and present RASP-Tuner, which instantiates a decomposition motivated by first principles: (i) identify a regime proxy by retrieving similar past contexts; (ii) predict short-horizon loss with a mixture-of-experts surrogate whose input concatenates parameters, context, and a retrieved soft prompt; (iii) adapt chiefly in a low-dimensional prompt subspace, invoking full surrogate updates only when scalarized error or disagreement spikes. A RealErrorComposer maps heterogeneous streaming metrics to [0,1] via EMA-stabilized logistic scores, supplying a single differentiable training target. On nine synthetic non-stationary benchmarks, an adversarial-context sanity check, and three tabular real-world streams (Section on real-world experiments), RASP-Tuner improves or matches cumulative regret relative to our GP-UCB and CMA-ES implementations on seven of nine synthetic tasks under paired tests at horizon T=100, while recording 8-12 times lower wall-clock per step than sliding-window GP-UCB on identical hardware. Idealized analysis in a cluster-separated, strongly convex regime model (RA-GD) supplies sufficient conditions for bounded dynamic regret; the deployed pipeline violates several of these premises, and we articulate which gaps remain open.

Related papers

• SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending [55.764018145256216]
  We present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor.<n>We show that SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.
  arXiv  Detail & Related papers  (2026-06-27T01:32:16Z)
• DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models [78.62380562116135]
  We propose DynT2I-Eval, a fully automated dynamic evaluation framework for text-to-image (T2I) models.<n>It constructs a structured visual semantic space from long-form descriptions, decomposing prompts into controllable dimensions.<n>DynT2I-Eval evaluates model performance across text alignment, perceptual quality, and aesthetics.
  arXiv  Detail & Related papers  (2026-05-07T12:53:51Z)
• Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration [41.34371852767098]
  CEA is a token-wise dynamic parameterization framework for all-in-one image restoration.<n>CEA improves average restoration quality over strong prompt-, descriptor-, and expert-based baselines.
  arXiv  Detail & Related papers  (2026-05-07T12:31:24Z)
• GSC-QEMit: A Telemetry-Driven Hierarchical Forecast-and-Bandit Framework for Adaptive Quantum Error Mitigation [2.3449366241547813]
  Quantum error mitigation (QEM) is essential for extracting reliable results from near-term quantum devices.<n>We introduce emphGSC-QEMit, a telemetry-driven, textbf-adaptive-forecast--bandit framework for emphcontext mitigation.<n>We evaluate GSC-QEMit on benchmark circuit families (GHZ, Quantum Fourier Transform, and Grover search) under nonstationary noise regimes simulated in Qiskit Aer.
  arXiv  Detail & Related papers  (2026-04-27T14:44:36Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• ReHARK: Refined Hybrid Adaptive RBF Kernels for Robust One-Shot Vision-Language Adaptation [3.8707695363745214]
  ReHARK is a training-free framework that reinterprets few-shot adaptation through global proximal regularization.<n>A new state-of-the-art for one-shot adaptation is established by ReHARK, which achieves an average accuracy of 65.83%.
  arXiv  Detail & Related papers  (2026-03-12T04:59:09Z)
• 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)
• SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training [54.8494905524997]
  Decentralized training introduces critical security risks when executed across untrusted, geographically distributed nodes.<n>We propose SENTINEL, a verification mechanism for pipeline parallelism (PP) training without duplication.<n>Experiments demonstrate successful training of up to 4B- parameter LLMs across untrusted distributed environments with up to 176 workers while maintaining model convergence and performance.
  arXiv  Detail & Related papers  (2026-03-03T23:51:10Z)
• Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment [27.352639822596146]
  Cross-worker divergence in losses and gradients can remain invisible under conventional monitoring signals.<n>We propose a model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines.
  arXiv  Detail & Related papers  (2026-02-16T04:42:30Z)
• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum [62.691095807959215]
  We establish an optimal sample complexity of $O(-2)$ for obtaining an $$-optimal global policy using a single-timescale actor-critic (AC) algorithm.<n>These mechanisms are compatible with existing deep learning architectures and require only minor modifications, without compromising practical applicability.
  arXiv  Detail & Related papers  (2026-02-02T00:35:42Z)
• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning [71.30276778807068]
  We propose a unified framework that strategically coordinates sample pruning and token pruning.<n>Q-Tuning achieves a +38% average improvement over the full-data SFT baseline using only 12.5% of the original training data.
  arXiv  Detail & Related papers  (2025-09-28T13:27:38Z)
• HyperTTA: Test-Time Adaptation for Hyperspectral Image Classification under Distribution Shifts [28.21559601586271]
  HyperTTA (Test-Time Adaptable Transformer for Hyperspectral Degradation) is a unified framework that enhances model robustness under diverse degradation conditions.<n>Test-time adaptation strategy, the Confidence-aware Entropy-minimized LayerNorm Adapter (CELA), dynamically updates only the affine parameters of LayerNorm layers.<n>Experiments on two benchmark datasets demonstrate that HyperTTA outperforms state-of-the-art baselines across a wide range of degradation scenarios.
  arXiv  Detail & Related papers  (2025-09-10T09:31:37Z)
• Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learning [1.3680468021400563]
  Few-shot adaptation remains a core challenge for vision-language models (VLMs)<n>We propose PromptFuseNL, a unified framework that enhances few-shot generalization by combining predictive prompt tuning with dual-branch positive and negative learning.
  arXiv  Detail & Related papers  (2025-05-16T23:39:34Z)

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.