PRBench: End-to-end Paper Reproduction in Physics Research

• URL: http://arxiv.org/abs/2603.27646v1
• Date: Sun, 29 Mar 2026 11:44:57 GMT
• Title: PRBench: End-to-end Paper Reproduction in Physics Research
• Abstract summary: PRBench is a benchmark of 30 expert-curated tasks spanning 11 subfields of physics.<n>Agents are provided only with the task instruction and paper content, and operate in a sandboxed execution environment.<n>We evaluate a set of coding agents on PRBench and analyze their capabilities across key dimensions of scientific reasoning and execution.
• Score: 32.672534450424386
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation and code generation. However, whether these agents can reliably perform end-to-end reproduction from real scientific papers remains an open question. We introduce PRBench, a benchmark of 30 expert-curated tasks spanning 11 subfields of physics. Each task requires an agent to comprehend the methodology of a published paper, implement the corresponding algorithms from scratch, and produce quantitative results matching the original publication. Agents are provided only with the task instruction and paper content, and operate in a sandboxed execution environment. All tasks are contributed by domain experts from over 20 research groups at the School of Physics, Peking University, each grounded in a real published paper and validated through end-to-end reproduction with verified ground-truth results and detailed scoring rubrics. Using an agentified assessment pipeline, we evaluate a set of coding agents on PRBench and analyze their capabilities across key dimensions of scientific reasoning and execution. The best-performing agent, OpenAI Codex powered by GPT-5.3-Codex, achieves a mean overall score of 34%. All agents exhibit a zero end-to-end callback success rate, with particularly poor performance in data accuracy and code correctness. We further identify systematic failure modes, including errors in formula implementation, inability to debug numerical simulations, and fabrication of output data. Overall, PRBench provides a rigorous benchmark for evaluating progress toward autonomous scientific research.

Related papers

• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• 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)
• Can Coding Agents Reproduce Findings in Computational Materials Science? [49.254975563645786]
  We present AutoMat, a benchmark for evaluating large language models' ability to reproduce scientific claims.<n>By working closely with subject matter experts, we curate a set of claims from real materials science papers to test whether coding agents can recover and execute the end-to-end workflow.<n>Results show that current LLM-based agents obtain low overall success rates on AutoMat, with the best-performing setting achieving a success rate of only 54.1%.
  arXiv  Detail & Related papers  (2026-05-01T17:42:12Z)
• AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery [55.70879973230979]
  AutoResearchBench is a benchmark for autonomous scientific literature discovery.<n>Compared to previous benchmarks on agentic web browsing, AutoResearchBench is research-oriented.<n>Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research.
  arXiv  Detail & Related papers  (2026-04-28T06:05:17Z)
• AIDABench: AI Data Analytics Benchmark [62.45908988324612]
  AIDABench is a benchmark for evaluating AI systems on complex data analytics tasks in an end-to-end manner.<n>AIDABench encompasses 600+ diverse document analysis tasks across three core capability dimensions: question answering, data visualization, and file generation.<n>We evaluate 11 state-of-the-art models on AIDABench, spanning both proprietary (e.g., Claude Sonnet 4.5, Gemini 3 Pro Preview) and open-source (e.g., Qwen3-Max-2026-01-23-Thinking) families.
  arXiv  Detail & Related papers  (2026-02-27T08:58:05Z)
• ResearchGym: Evaluating Language Model Agents on Real-World AI Research [48.46915933681714]
  We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research.<n>To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL.<n>In a controlled evaluation of an agent powered by GPT-5, we observe a sharp capability--reliability gap.
  arXiv  Detail & Related papers  (2026-02-16T19:00:03Z)
• AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents [49.67355440164857]
  We introduce AIRS-Bench, a suite of 20 tasks sourced from state-of-the-art machine learning papers.<n>Airs-Bench tasks assess agentic capabilities over the full research lifecycle.<n>We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.
  arXiv  Detail & Related papers  (2026-02-06T16:45:02Z)
• ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers? [29.17900668495058]
  We introduce ReplicationBench, an evaluation framework for frontier AI agents.<n>It tests whether agents can replicate entire research papers drawn from the astrophysics literature.<n>R ReplicationBench establishes the first benchmark of paper-scale, expert-validated astrophysics research tasks.
  arXiv  Detail & Related papers  (2025-10-28T16:21:19Z)
• RExBench: Can coding agents autonomously implement AI research extensions? [14.147417159347448]
  Agents based on Large Language Models (LLMs) have shown promise for performing sophisticated software engineering tasks autonomously.<n>We argue that research extension and its implementation is a critical capability for such systems.<n>We introduce RExBench to support the evaluation of this capability.
  arXiv  Detail & Related papers  (2025-06-27T19:41:41Z)
• FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks [52.47895046206854]
  FieldWorkArena is a benchmark for agentic AI targeting real-world field work.<n>This paper defines a new action space that agentic AI should possess for real world work environment benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T08:21:46Z)
• PaperBench: Evaluating AI's Ability to Replicate AI Research [3.4567792239799133]
  PaperBench is a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.<n>Agents must replicate 20 ICML 2024 Spotlight and Oral papers from scratch.<n>PaperBench contains 8,316 individually gradable tasks.
  arXiv  Detail & Related papers  (2025-04-02T15:55:24Z)
• ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery [23.773528748933934]
  We present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery.<n>We extract 102 tasks from 44 peer-reviewed publications in four disciplines and engage nine subject matter experts to validate them.<n>Using ScienceAgentBench, we evaluate five open-weight and proprietary LLMs, each with three frameworks: direct prompting, OpenHands CodeAct, and self-AI.
  arXiv  Detail & Related papers  (2024-10-07T14:33:50Z)

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.