Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation

Lingyue Fu, Bolun Zhang, Hao Guan, Yaoming Zhu +6 more

Published

Oct 28, 2025

Citations

0

Trust level

High

Usefulness score

77/100 (High)

Extraction confidence

75% (High)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Mar 23, 2026

Open arXiv Open DOI Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Coding Expert Verification Llm As Judge

Should you rely on this paper?

This paper has strong direct human-feedback and evaluation protocol signal and is suitable as a primary eval pipeline reference.

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

Best use

Primary protocol reference for eval design

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

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

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
77/100
High-confidence candidate

Use this as a primary source when designing or comparing eval protocols.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs). However, existing benchmarks for code agent evaluation face two major limitations. First, creating high-quality project-level evaluation datasets requires extensive domain expertise, leading to prohibitive annotation costs and limited diversity. Second, while recent Agent-as-a-Judge paradigms address the rigidity of traditional unit tests by enabling flexible metrics, their reliance on In-Context Learning (ICL) with general LLMs often results in inaccurate assessments that misalign with human standards. To address these challenges, we propose an agent-driven benchmark construction pipeline that leverages human supervision to efficiently generate diverse project-level tasks. Based on this, we introduce PRDBench, comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Documents (PRDs) and comprehensive criteria. Furthermore, to overcome the inaccuracy of general LLM judges, we propose a highly reliable evaluation framework powered by a specialized, fine-tuned model. Based on Qwen3-Coder-30B, our dedicated PRDJudge achieves over 90% human alignment in fixed-interface scenarios. Extensive experiments demonstrate that our suite provides a scalable, robust, and highly accurate framework for assessing state-of-the-art code agents.

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

Expert Verification

Directly usable for protocol triage.

"Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs)."

Evaluation Modes

strong

Llm As Judge, Automatic Metrics

Includes extracted eval setup.

"Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs)."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs)."

Benchmarks / Datasets

strong

Prdbench

Useful for quick benchmark comparison.

"Based on this, we introduce PRDBench, comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Documents (PRDs) and comprehensive criteria."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs)."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"First, creating high-quality project-level evaluation datasets requires extensive domain expertise, leading to prohibitive annotation costs and limited diversity."

Benchmarks and datasets

Prdbench

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Expert Verification
Rater population
Domain Experts
Expertise required
Coding
Evaluation details
Evaluation modes
Llm As Judge, Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
High
Use this page as
Primary protocol reference for eval design

Research brief

Metadata summary

Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs).

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

Key takeaways

  • Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs).
  • However, existing benchmarks for code agent evaluation face two major limitations.
  • First, creating high-quality project-level evaluation datasets requires extensive domain expertise, leading to prohibitive annotation costs and limited diversity.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • 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

Contribution summary

  • To address these challenges, we propose an agent-driven benchmark construction pipeline that leverages human supervision to efficiently generate diverse project-level tasks.
  • Based on this, we introduce PRDBench, comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Documents (PRDs) and comprehensive criteria.
  • Furthermore, to overcome the inaccuracy of general LLM judges, we propose a highly reliable evaluation framework powered by a specialized, fine-tuned model.

Why it matters for eval

  • To address these challenges, we propose an agent-driven benchmark construction pipeline that leverages human supervision to efficiently generate diverse project-level tasks.
  • Furthermore, to overcome the inaccuracy of general LLM judges, we propose a highly reliable evaluation framework powered by a specialized, fine-tuned model.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Expert Verification

  • Evaluation mode is explicit

    Detected: Llm As Judge, Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: Prdbench

  • Metric reporting is present

    No metric terms extracted.