An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc

• URL: http://arxiv.org/abs/2603.15976v1
• Date: Mon, 16 Mar 2026 22:46:10 GMT
• Title: An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc
• Abstract summary: petscagent-bench is an agentic framework built on an agents-evaluating-agents paradigm.<n>It orchestrates a 14-evaluator pipeline across five scoring categories: correctness, performance, code quality, algorithmic appropriateness, and library-specific conventions.<n>We demonstrate the framework on a benchmark suite of realistic problems using the PETSc library for HPC.
• Score: 7.236134946837382
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach insufficient for library code in HPC where solver selection, API conventions, memory management, and performance are just as critical as functional correctness. To address this gap, we introduce petscagent-bench, an agentic framework built on an agents-evaluating-agents paradigm. Instead of relying on static scripts, petscagent-bench deploys a tool-augmented evaluator agent that compiles, executes, and measures code produced by a separate model-under-test agent, orchestrating a 14-evaluator pipeline across five scoring categories: correctness, performance, code quality, algorithmic appropriateness, and library-specific conventions. Because the agents communicate through standardized protocols (A2A and MCP), the framework enables black-box evaluation of any coding agent without requiring access to its source code. We demonstrate the framework on a benchmark suite of realistic problems using the PETSc library for HPC. Our empirical analysis of frontier models reveals that while current models generate readable, well-structured code, they consistently struggle with library-specific conventions that traditional pass/fail metrics completely miss.

Related papers

• Code as Representation: A Compilable Parsing Paradigm for Academic Documents [50.40789738182074]
  Compilable Academic Document Parsing (CADP) is a paradigm that reconstructs a full page as contextual La plus executable Python.<n>We introduce CADP-Bench, an expert-verified benchmark of full academic pages containing text and multiple SAE types.<n>Results show that even frontier models still struggle to produce high-fidelity executable reconstructions.
  arXiv  Detail & Related papers  (2026-08-18T09:10:43Z)
• 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)
• From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence [12.026104106923556]
  Industrial Prognostics and Health Management provides a representative case study for translating published papers into executable, benchmark-ready implementations.<n>We introduce emphagentic, framework-based PHM paper reproduction, where an agent translates a paper into a shared PHM benchmark framework via a emphslot-binding interface.<n>We evaluate this approach on 16 PHM papers, comparing framework-enhanced, skill-based and prompt-based agentic reproduction against a recent framework-free paper-reproduction agent.
  arXiv  Detail & Related papers  (2026-05-27T12:11:05Z)
• Automating Formal Verification with Agent-Guided Tree Search [0.0]
  Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production.<n>Recent benchmarks measure their ability to translate specifications into code and machine-checked iteration of correctness.<n>This thesis evaluates the state of such LLM-driven verified-code generation in Lean and develops search-based methods for improving performance.
  arXiv  Detail & Related papers  (2026-05-26T14:50:47Z)
• Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction [0.02446672595462589]
  We introduce Collider-Bench, a benchmark for evaluating whether language-model agents can reproduce experimental analyses from the Large Hadron Collider (LHC) using only public papers and open scientific software.<n>Agents must therefore rely on physical reasoning, domain knowledge, and trial-and-error to fill these gaps.<n>Our results show that on average no agent reliably beats the physicist-in-the-loop solution.
  arXiv  Detail & Related papers  (2026-05-13T18:00:00Z)
• CR-Bench: Evaluating the Real-World Utility of AI Code Review Agents [0.7496422063843831]
  We introduce CR-Bench, a benchmarking dataset, and CR-Evaluator, a fine-grained evaluation pipeline for code review agents.<n>We find that code review agents can exhibit a low signal-to-noise ratio when designed to identify all hidden issues.<n>Our analysis identifies the hidden trade-off between issue resolution and spurious findings, revealing a frontier that constrains effective agent design.
  arXiv  Detail & Related papers  (2026-03-10T21:29:42Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• Do Large Language Models Respect Contracts? Evaluating and Enforcing Contract-Adherence in Code Generation [11.445615378917578]
  PACT is a program assessment and contract-adherence evaluation framework.<n>It provides a comprehensive test-suite corpus focused on contract violations.<n>It enables a systematic analysis of code generation under varied prompting conditions.
  arXiv  Detail & Related papers  (2025-10-14T01:12:37Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• Alignment with Fill-In-the-Middle for Enhancing Code Generation [56.791415642365415]
  We propose a novel approach that splits code snippets into smaller, granular blocks, creating more diverse DPO pairs from the same test cases.<n>Our approach demonstrates significant improvements in code generation tasks, as validated by experiments on benchmark datasets such as HumanEval (+), MBPP (+), APPS, LiveCodeBench, and BigCodeBench.
  arXiv  Detail & Related papers  (2025-08-27T03:15:53Z)
• Commit0: Library Generation from Scratch [77.38414688148006]
  Commit0 is a benchmark that challenges AI agents to write libraries from scratch.<n>Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests.<n> Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate.
  arXiv  Detail & Related papers  (2024-12-02T18:11:30Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• RepoMasterEval: Evaluating Code Completion via Real-World Repositories [14.744942194298673]
  RepoMasterEval is a novel benchmark for evaluating code completion models constructed from real-world repositories.<n>Each benchmark is generated by masking a code snippet from one source code file with existing test suites.
  arXiv  Detail & Related papers  (2024-08-07T03:06:57Z)
• SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [10.730852617039451]
  We investigate the capability of LLM-based Code Agents to formalize user issues into test cases.<n>We propose a novel benchmark based on popular GitHub repositories, containing real-world issues, ground-truth bug-fixes, and golden tests.<n>We find that LLMs generally perform surprisingly well at generating relevant test cases, with Code Agents designed for code repair exceeding the performance of systems designed for test generation.
  arXiv  Detail & Related papers  (2024-06-18T14:54:37Z)

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.