Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning

• URL: http://arxiv.org/abs/2602.18922v1
• Date: Sat, 21 Feb 2026 18:25:18 GMT
• Title: Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning
• Abstract summary: Cache effectiveness requires key consistency and precision, not classification accuracy.<n>We introduce W5H2, a structured intent decomposition framework.<n>On NyayaBench v2 (20 classes), SetFit achieves 55.3%, with cross-lingual transfer across 30 languages.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property -- cache effectiveness requires key consistency and precision, not classification accuracy. We observe cache-key evaluation reduces to clustering evaluation and apply V-measure decomposition to separate these on n=8,682 points across MASSIVE, BANKING77, CLINC150, and NyayaBench v2, our new 8,514-entry multilingual agentic dataset (528 intents, 20 W5H2 classes, 63 languages). We introduce W5H2, a structured intent decomposition framework. Using SetFit with 8 examples per class, W5H2 achieves 91.1%+/-1.7% on MASSIVE in ~2ms -- vs 37.9% for GPTCache and 68.8% for a 20B-parameter LLM at 3,447ms. On NyayaBench v2 (20 classes), SetFit achieves 55.3%, with cross-lingual transfer across 30 languages. Our five-tier cascade handles 85% of interactions locally, projecting 97.5% cost reduction. We provide risk-controlled selective prediction guarantees via RCPS with nine bound families.

Related papers

• Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement [0.05999777817331314]
  We evaluate a 10-qubit hybrid quantum-classical variational circuit for paraphrase detection.<n>On QQP the circuit achieves 75.53% +/- 0.75% accuracy.<n>On MRPC the optimal 2-layer variant reaches 92% of BERT-base accuracy at 54,000 lower parameter cost.<n>These results constitute the first systematic parameter-matched multi-benchmark empirical validation of hybrid variational circuits for NLP.
  arXiv  Detail & Related papers  (2026-09-13T14:06:49Z)
• Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency [0.0]
  This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet.<n>We report top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 storage, GMACs, batch-size-1 latency on an NVIDIA L4 and AMD 5 5500U CPU.
  arXiv  Detail & Related papers  (2026-07-02T10:14:07Z)
• VisualClaw: A Real-Time, Personalized Agent for the Physical World [76.89211120690028]
  We present VisualClaw, a self-evolving multimodal agent built around two principles.<n>First, hybrid encoding reduces deployment cost by filtering less informative streaming frames with a cascaded gate.<n>Second, skill evolution lets the agent learn from failures, producing skill-bank updates that help future questions.
  arXiv  Detail & Related papers  (2026-06-15T06:58:22Z)
• PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks [15.973951643113963]
  PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization.<n>On our in-house benchmarks, PP-OCRv6_medium achieves 83.2% recognition accuracy and 86.2% detection Hmean.
  arXiv  Detail & Related papers  (2026-06-11T09:35:16Z)
• EfficientSign: An Attention-Enhanced Lightweight Architecture for Indian Sign Language Recognition [3.4772255133148366]
  We build a lightweight model which takes EfficientNet-B0 and focuses on two attention modules.<n>We tested it against five other approaches on 12,637 images of Indian Sign Language alphabets.
  arXiv  Detail & Related papers  (2026-04-09T18:27:57Z)
• Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement [3.7765281299298015]
  We study on-device time-series analysis for gait detection in Parkinson's disease (PD) from short windows of triaxial acceleration, targeting resource-latency wearables and edge nodes.<n>We compare magnitude thresholding to three 1D CNNs for time-series analysis: a literature baseline (separable convolutions) and two ultra-light models - one purely separable and one with residual connections.
  arXiv  Detail & Related papers  (2025-11-29T08:52:41Z)
• Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training [0.0]
  This work presents a systematic investigation of custom convolutional neural network architectures for satellite land use classification.<n>We achieve 97.23% test accuracy on the EuroSAT dataset without reliance on pre-trained models.<n>Our approach achieves performance within 1.34% of fine-tuned ResNet-50 (98.57%) while requiring no external data.
  arXiv  Detail & Related papers  (2025-10-17T10:59:24Z)
• Learnable Conformal Prediction with Context-Aware Nonconformity Functions for Robotic Planning and Perception [4.694504497452662]
  Learnable Conformal Prediction replaces fixed scores with a lightweight neural function to produce context-aware uncertainty sets.<n>It maintains CP's theoretical guarantees while reducing prediction set sizes by 18% in classification, tightening detection intervals by 52%, and improving path planning safety from 72% to 91% success with minimal overhead.<n> Hardware evaluation shows LCP adds less than 1% memory and 15.9% inference overhead, yet sustains 39 FPS on detection tasks while being 7.4 times more energy-efficient than ensembles.
  arXiv  Detail & Related papers  (2025-09-26T06:44:58Z)
• vCache: Verified Semantic Prompt Caching [95.16654660556975]
  This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
  arXiv  Detail & Related papers  (2025-02-06T04:16:20Z)
• SINF: Semantic Neural Network Inference with Semantic Subgraphs [3.767257257405998]
  This paper proposes Semantic Inference (SINF) that creates semantic subgraphs in a Deep Neural Network(DNN) based on a new Discriminative Capability Score (DCS)<n>We evaluate the performance SINF on VGG16, VGG19, and ResNet50 DNNs trained on CIFAR100 and a subset of the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-10-02T14:51:10Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data [122.282521548393]
  Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning.<n>We introduce HELIP, a cost-effective strategy that improves CLIP models by exploiting challenging text-image pairs within existing datasets in continuous training.
  arXiv  Detail & Related papers  (2023-05-09T07:00:17Z)
• Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems [63.713297451300086]
  We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B. Their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
  arXiv  Detail & Related papers  (2022-06-15T20:44:23Z)
• PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices [13.62426382827205]
  PP-PicoDet family of real-time object detectors achieves superior performance on object detection for mobile devices. Models achieve better trade-offs between accuracy and latency compared to other popular models.
  arXiv  Detail & Related papers  (2021-11-01T12:53:17Z)
• Comment on Stochastic Polyak Step-Size: Performance of ALI-G [104.83776736573009]
  ALI-G and SPS are both adaptations of the Polyak step-size to optimize machine learning models. We show that when training a ResNet-34 on CIFAR-10 and CIFAR-100, the performance of ALI-G can reach respectively 93.5% (+6%) and 76% (+8%) with a very small amount of tuning.
  arXiv  Detail & Related papers  (2021-05-20T19:57:34Z)
• Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model [6.338178373376447]
  We investigate if the wav2vec 2.0 self-supervised pretraining helps mitigate the overfitting issues with connectionist temporal classification. For supervised adaptation of the wav2vec 2.0 model, both E2E-LFMMI and CTC achieve similar results. For Babel languages, we obtain relative improvements of 26% and 23% on Swahili (38h) and 18% and 17% on Tagalog (84h) respectively.
  arXiv  Detail & Related papers  (2021-04-06T14:56:04Z)
• Non-Parametric Adaptive Network Pruning [125.4414216272874]
  We introduce non-parametric modeling to simplify the algorithm design. Inspired by the face recognition community, we use a message passing algorithm to obtain an adaptive number of exemplars. EPruner breaks the dependency on the training data in determining the "important" filters.
  arXiv  Detail & Related papers  (2021-01-20T06:18:38Z)
• Second-Order Provable Defenses against Adversarial Attacks [63.34032156196848]
  We show that if the eigenvalues of the network are bounded, we can compute a certificate in the $l$ norm efficiently using convex optimization. We achieve certified accuracy of 5.78%, and 44.96%, and 43.19% on 2,59% and 4BP-based methods respectively.
  arXiv  Detail & Related papers  (2020-06-01T05:55:18Z)

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.