Skip to content
← Back to explorer

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

Abhinaba Basu · Feb 21, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this paper page

Coverage: Stale

Use this page to decide whether the paper is strong enough to influence an eval design. It summarizes the abstract plus available structured metadata. If the signal is thin, use it as background context and compare it against stronger hub pages before making protocol choices.

Best use

Background context only

Metadata: Stale

Trust level

Low

Signals: Stale

What still needs checking

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Signal confidence: 0.45

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.

Use caution before copying this protocol

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.45 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

5/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What This Page Found In The Paper

Each field below shows whether the signal looked explicit, partial, or missing in the available metadata. Use this to judge what is safe to trust directly and what still needs full-paper validation.

Human Feedback Types

missing

None explicit

Confidence: Low Not found

No explicit feedback protocol extracted.

Evidence snippet: Personal AI agents incur substantial cost via repeated LLM calls.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Direct evidence

Includes extracted eval setup.

Evidence snippet: Personal AI agents incur substantial cost via repeated LLM calls.

Quality Controls

missing

Not reported

Confidence: Low Not found

No explicit QC controls found.

Evidence snippet: Personal AI agents incur substantial cost via repeated LLM calls.

Benchmarks / Datasets

partial

Nyayabench

Confidence: Low Direct evidence

Useful for quick benchmark comparison.

Evidence snippet: 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).

Reported Metrics

partial

Accuracy, Precision, Cost

Confidence: Low Direct evidence

Useful for evaluation criteria comparison.

Evidence snippet: Personal AI agents incur substantial cost via repeated LLM calls.

Rater Population

missing

Unknown

Confidence: Low Not found

Rater source not explicitly reported.

Evidence snippet: Personal AI agents incur substantial cost via repeated LLM calls.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Multilingual
  • Signal basis: Structured extraction plus abstract evidence.

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Signal confidence: 0.45
  • Known cautions: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

Nyayabench

Reported Metrics

accuracyprecisioncost

Research Brief

Metadata summary

Personal AI agents incur substantial cost via repeated LLM calls.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • 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.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Accuracy

Research Summary

Contribution Summary

  • 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%.
  • We introduce W5H2, a structured intent decomposition framework.

Why It Matters For Eval

  • 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%.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: Nyayabench

  • Pass: Metric reporting is present

    Detected: accuracy, precision, cost

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now