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

• URL: http://arxiv.org/abs/2510.24358v1
• Date: Tue, 28 Oct 2025 12:26:45 GMT
• Title: Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation
• Abstract summary: PRDBench is a novel benchmark comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Document (PRD) requirements, comprehensive evaluation criteria, and reference implementations.<n>We employ an Agent-as-a-Judge paradigm to score agent outputs, enabling the evaluation of various test types beyond unit tests.
• Score: 47.85891728056131
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs) and widely adopted tools. However, existing benchmarks for code agent evaluation face two major limitations: high annotation cost and expertise requirements, and rigid evaluation metrics that rely primarily on unit tests. To address these challenges, we propose an agent-driven benchmark construction pipeline that leverages human supervision to efficiently generate diverse and challenging project-level tasks. Based on this approach, we introduce PRDBench, a novel benchmark comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Document (PRD) requirements, comprehensive evaluation criteria, and reference implementations. PRDBench features rich data sources, high task complexity, and flexible metrics. We further employ an Agent-as-a-Judge paradigm to score agent outputs, enabling the evaluation of various test types beyond unit tests. Extensive experiments on PRDBench demonstrate its effectiveness in assessing the capabilities of both code agents and evaluation agents, providing a scalable and robust framework for annotation and evaluation.

Related papers

• Benchmark Everything Everywhere All at Once [28.30618112297148]
  We introduce Benchmark Agent, a fully autonomous agentic system designed for benchmark building.<n>Our framework orchestrates the complete benchmark construction pipeline, from user query analysis and subtask design to data annotation and quality control.<n>We produce 15 representative benchmarks, spanning diverse evaluation scenarios, including text understanding, multimodal understanding, and domain-specific reasoning.
  arXiv  Detail & Related papers  (2026-06-04T17:52:04Z)
• The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? [80.24951682268332]
  We introduce the Meta-Agent Challenge (MAC), an evaluation framework designed to test the capacity of frontier models for autonomous agent development.<n>To ensure evaluation integrity, this framework is secured by multi-layer defenses against reward hacking.<n>We demonstrate that meta-agents rarely match human-engineered baseline policies, and the few that do are dominated by proprietary frontier models.
  arXiv  Detail & Related papers  (2026-06-03T04:58:17Z)
• AlphaEval: Evaluating Agents in Production [32.52315519888507]
  We present AlphaEval, a production-grounded benchmark of 94 tasks sourced from seven companies deploying AI agents in their core business.<n>Unlike model-centric benchmarks, AlphaEval evaluates complete agent products as commercial systems, capturing performance variations invisible to model-level evaluation.
  arXiv  Detail & Related papers  (2026-04-14T00:43:20Z)
• Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution [5.10403054516716]
  Existing datasets evaluate performance on isolated, single pull request (PR) tasks in a stateless manner.<n>We introduce an automated coding task generation framework, which helps generate our dataset SWE-STEPS.
  arXiv  Detail & Related papers  (2026-04-03T13:44:40Z)
• AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios [49.90735676070039]
  The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow.<n>We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks.<n>We propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks.
  arXiv  Detail & Related papers  (2026-01-28T13:49:18Z)
• LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
  We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
  arXiv  Detail & Related papers  (2025-11-17T23:57:24Z)
• Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agents [23.277131100190086]
  We propose a process of benchmark generation that helps evolve the benchmarks as the requirements change and perform robust evaluation of evolving AI agents.<n>Our approach relies on semi-structured documents where developers express the high-level intent, and uses state-of-the-art LLMs to generate benchmarks from just a small number of such documents.
  arXiv  Detail & Related papers  (2025-11-13T07:48:22Z)
• A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports [24.09178055088843]
  Deep Research Agents (DRAs) exhibit the capabilities for task decomposition, cross-source retrieval, multi-stage reasoning, and structured output.<n>This paper introduces a rigorous benchmark and a multidimensional evaluation framework tailored to DRAs and report-style responses.<n>The framework enables comprehensive evaluation of long-form reports generated by DRAs, incorporating integrated scoring metrics for semantic quality, topical focus, and retrieval trustworthiness.
  arXiv  Detail & Related papers  (2025-10-02T16:40:02Z)
• RefactorCoderQA: Benchmarking LLMs for Multi-Domain Coding Question Solutions in Cloud and Edge Deployment [20.416910591388618]
  We introduce RefactorCoderQA, a benchmark designed to evaluate and enhance the performance of Large Language Models (LLMs) across coding tasks.<n>Our fine-tuned model, RefactorCoder-MoE, achieves state-of-the-art performance, significantly outperforming leading open-source and commercial baselines with an overall accuracy of 76.84%.
  arXiv  Detail & Related papers  (2025-09-12T17:44:22Z)
• MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models [76.72220653705679]
  We introduce MCPEval, an open-source framework that automates end-to-end task generation and deep evaluation of intelligent agents.<n> MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines.<n> Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance.
  arXiv  Detail & Related papers  (2025-07-17T05:46:27Z)
• AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios [51.46347732659174]
  Large Language Models (LLMs) have demonstrated advanced capabilities in real-world agentic applications.<n>AgentIF is the first benchmark for systematically evaluating LLM instruction following ability in agentic scenarios.
  arXiv  Detail & Related papers  (2025-05-22T17:31:10Z)
• OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain [62.89809156574998]
  We introduce an omnidirectional and automatic RAG benchmark, OmniEval, in the financial domain.<n>Our benchmark is characterized by its multi-dimensional evaluation framework.<n>Our experiments demonstrate the comprehensiveness of OmniEval, which includes extensive test datasets.
  arXiv  Detail & Related papers  (2024-12-17T15:38:42Z)
• BenchAgents: Multi-Agent Systems for Structured Benchmark Creation [23.653678381444276]
  BenchAgents is a framework that automates the creation of evaluation benchmarks.<n>We use BenchAgents to create benchmarks to evaluate capabilities related to planning, constraint satisfaction, and causal reasoning.<n>We then use these benchmarks to study state-of-the-art models and extract new insights into common failure modes and model differences.
  arXiv  Detail & Related papers  (2024-10-29T22:56:18Z)
• TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domains [19.492393243160244]
  Large Language Models (LLMs) are increasingly deployed in highly specialized vertical domains.<n>Existing evaluations for vertical domains typically rely on the labor-intensive construction of static single-turn datasets.<n>We propose TestAgent, a framework for automatic benchmarking and exploratory dynamic evaluation in vertical domains.
  arXiv  Detail & Related papers  (2024-10-15T11:20:42Z)
• PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models [72.57329554067195]
  ProxyQA is an innovative framework dedicated to assessing longtext generation. It comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. It assesses the generated content's quality through the evaluator's accuracy in addressing the proxy-questions.
  arXiv  Detail & Related papers  (2024-01-26T18:12:25Z)

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.