Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

PACE: A Proxy for Agentic Capability Evaluation

Yueqi Song, Lintang Sutawika, Jiarui Liu, Lindia Tjuatja, Jiayi Geng, Yunze Xiao, Daniel Lee, Aditya Bharat Soni, Vincent Lo, Xiang Yue, Graham Neubig · Jul 2, 2026 · Citations: 0

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

How to use this page

High trust

Use this as a practical starting point for protocol research, then validate against the original paper.

Best use

Secondary protocol comparison source

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

High

Derived from extracted protocol signals and abstract evidence.

Abstract

Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation can cost thousands of dollars and take days to complete. In contrast, non-agentic LLM benchmarks that test individual capabilities (e.g., reasoning, code generation) are fast and cheap to run. In this paper, we investigate whether performance on expensive agentic benchmarks can be accurately predicted by the performance on a small, carefully selected subset of atomic evaluation instances. We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations whose aggregate scores most reliably predict model performances on agentic benchmarks. Given a pool of candidate instances spanning atomic capabilities, PACE fits a regression that maps a model's scores on a compact subset of source instances to its score on the target agentic benchmark. The subset itself is curated by combining two complementary instance-selection strategies, target-relevance local selection and globally informative global selection. We apply PACE to the 4 target agentic benchmarks in this paper, which yields PACE-Bench, the concrete proxy benchmark that we evaluate in the paper. Experiments across 14 models, 4 agentic benchmarks, and 19 non-agentic benchmarks show that PACE-Bench predicts agentic scores with leave-one-out cross-validation (LOOCV) mean absolute error (MAE) under 4%, Spearman correlation above 0.80, and pairwise model-ranking accuracy around 85%, all at much less than 1% of the full agentic evaluation cost. We further analyze the selected proxy instances, revealing which skills each agentic benchmark uniquely demands. PACE enables practitioners to obtain reliable estimates of agentic performance during model development, selection, and routing, without the overhead of full agent evaluation.

Should You Rely On This Paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

No major weakness surfaced.

Trust level

High

Usefulness score

65/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

Usefulness for eval research

Moderate-confidence candidate

Extraction confidence 80%

If you are doing eval pipeline work, start here:

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

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Pairwise Preference

Directly usable for protocol triage.

"Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure."

Benchmarks / Datasets

strong

GAIA, SWE Bench, Pace Bench

Useful for quick benchmark comparison.

"Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure."

Reported Metrics

strong

Accuracy, Spearman, Mae, Relevance

Useful for evaluation criteria comparison.

"The subset itself is curated by combining two complementary instance-selection strategies, target-relevance local selection and globally informative global selection."

Human Feedback Details

  • Uses human feedback: Yes
  • Feedback types: Pairwise Preference
  • Rater population: Not reported
  • Unit of annotation: Pairwise
  • Expertise required: Coding

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: High
  • Use this page as: Secondary protocol comparison source

Protocol And Measurement Signals

Benchmarks / Datasets

GAIASWE-benchPace-Bench

Reported Metrics

accuracyspearmanmaerelevance

Research Brief

Metadata summary

Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure.

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

Key Takeaways

  • Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure.
  • A single evaluation can cost thousands of dollars and take days to complete.
  • In contrast, non-agentic LLM benchmarks that test individual capabilities (e.g., reasoning, code generation) are fast and cheap to run.

Researcher Actions

  • Compare this paper against others mentioning SWE-bench.
  • 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.

Research Summary

Contribution Summary

  • We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations whose aggregate scores most reliably predict model performances on agentic benchmarks.
  • We apply PACE to the 4 target agentic benchmarks in this paper, which yields PACE-Bench, the concrete proxy benchmark that we evaluate in the paper.
  • Experiments across 14 models, 4 agentic benchmarks, and 19 non-agentic benchmarks show that PACE-Bench predicts agentic scores with leave-one-out cross-validation (LOOCV) mean absolute error (MAE) under 4%, Spearman correlation above 0.80,…

Why It Matters For Eval

  • We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations whose aggregate scores most reliably predict model performances on agentic benchmarks.
  • We apply PACE to the 4 target agentic benchmarks in this paper, which yields PACE-Bench, the concrete proxy benchmark that we evaluate in the paper.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Pairwise Preference

  • 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: GAIA, SWE-bench, Pace-Bench

  • Pass: Metric reporting is present

    Detected: accuracy, spearman, mae, relevance

Related Papers

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