Towards grounded autonomous research: an end-to-end LLM mini research loop on published computational physics

• URL: http://arxiv.org/abs/2604.12198v1
• Date: Tue, 14 Apr 2026 02:06:59 GMT
• Title: Towards grounded autonomous research: an end-to-end LLM mini research loop on published computational physics
• Abstract summary: Recent autonomous LLM agents have demonstrated end-to-end automation of machine-learning research.<n>We focus on the smallest meaningful unit of such research, a mini research loop in which an agent reads a paper, reproduces it, critiques it, and extends it.<n>We test this loop in two complementary regimes: scale and depth.
• Score: 3.7193230342956056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent autonomous LLM agents have demonstrated end-to-end automation of machine-learning research. Real-world physical science is intrinsically harder, requiring deep reasoning bounded by physical truth and, because real systems are too complex to study in isolation, almost always built on existing literature. We focus on the smallest meaningful unit of such research, a mini research loop in which an agent reads a paper, reproduces it, critiques it, and extends it. We test this loop in two complementary regimes: scale and depth. At scale, across 111 open-access computational physics papers, an agent autonomously runs the read-plan-compute-compare loop and, without being asked to critique, raises substantive concerns on ~42% of papers - 97.7% of which require execution to surface. In depth, for one Nature Communications paper on multiscale simulation of a 2D-material MOSFET, the agent runs new calculations missing from the original and produces, unsupervised, a publishable Comment -- composed, figured, typeset, and PDF-iterated -- that revises the paper's headline conclusion.

Related papers

• ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System [29.871573462927643]
  We introduce ReasFlow, an end-to-end autonomous agent system for reasoning-centric scientific discovery.<n>The system unifies literature synthesis, algorithm design, theorem proving, experimentation, and manuscript preparation in a single system.<n>ReasFlow is publicly accessible via the ReasLab platform, providing a collaborative workspace for AI-assisted theoretical research.
  arXiv  Detail & Related papers  (2026-07-15T13:27:20Z)
• Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics [3.7193230342956056]
  We present a pipeline that runs end-to-end from a corpus of 11,083 recent condensed-matter physics arXiv papers to a publication-grade manuscript.<n>Fault tolerance emerges from redundancy: fresh-context isolation, distributed grounding, and adversarial review catch what any single session misses.<n>The primitives, characterized failure modes, and quantified intervention pattern lay a foundation for autonomous research in high-stakes scientific domains.
  arXiv  Detail & Related papers  (2026-07-02T15:35:41Z)
• ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research [142.29356526274387]
  We present ResearchClawBench, a benchmark for evaluating autonomous scientific research.<n>Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation.
  arXiv  Detail & Related papers  (2026-05-28T16:27:40Z)
• 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)
• End-to-end autonomous scientific discovery on a real optical platform [12.355486051983162]
  Qiushi Discovery Engine is an LLM-based agentic system for end-to-end autonomous scientific discovery on a real optical platform.<n>It reproduces a published transmission-matrix experiment on a non-original platform and converts an abstract coherence-order theory into experimental observables.<n>This is the first demonstration of an AI agentic system autonomously identifying and experimentally validating a nontrivial, previously unreported physical mechanism.
  arXiv  Detail & Related papers  (2026-04-29T18:36:57Z)
• 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)
• pAI/MSc: ML Theory Research with Humans on the Loop [0.6335848702857036]
  pAI/MSc is an open-source, customizable, modular multi-agent system for academic research ideation.<n>It reduces by orders of the human steering required to turn a specified hypothesis into a literature-grounded, mathematically established, experimentally supported, submission-oriented manuscript draft.
  arXiv  Detail & Related papers  (2026-04-22T14:38:28Z)
• An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
  Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
  arXiv  Detail & Related papers  (2025-12-22T15:03:57Z)
• Seismology modeling agent: A smart assistant for geophysical researchers [14.28965530601497]
  This paper proposes an intelligent, interactive workflow powered by Large Language Models (LLMs)<n>We introduce the first Model Context Protocol (MCP) server suite for SPECFEM.<n>The framework supports both fully automated execution and human-in-the-loop collaboration.
  arXiv  Detail & Related papers  (2025-12-16T14:18:26Z)
• Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprints [15.070885964897734]
  Generative large language models (LLMs) introduce a further potential disruption by altering how manuscripts are written.<n>This paper addresses the gap through a large-scale analysis of more than 2.1 million preprints spanning 2016--2025 (115 months) across four major repositories.<n>Our findings reveal that LLMs have accelerated submission and revision cycles, modestly increased linguistic complexity, and disproportionately expanded AI-related topics.
  arXiv  Detail & Related papers  (2025-10-18T01:37:40Z)
• Leveraging LLMs for Semi-Automatic Corpus Filtration in Systematic Literature Reviews [5.911820207772152]
  We propose a pipeline leveraging multiple large language models (LLMs), classifying papers based on descriptive prompts and deciding jointly.<n>The entire process is human-supervised and interactively controlled via our open-source visual analytics web interface, LLMSurver.<n>Results demonstrate that our pipeline significantly reduces manual effort while achieving lower error rates than single human annotators.
  arXiv  Detail & Related papers  (2025-10-13T13:48:29Z)
• LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation [66.09346158850308]
  We present LiRA (Literature Review Agents), a multi-agent collaborative workflow which emulates the human literature review process.<n>LiRA utilizes specialized agents for content outlining, subsection writing, editing, and reviewing, producing cohesive and comprehensive review articles.<n>We evaluate LiRA in real-world scenarios using document retrieval and assess its robustness to reviewer model variation.
  arXiv  Detail & Related papers  (2025-10-01T12:14:28Z)
• Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark [49.42250115889234]
  We present the first benchmark designed to test large language models (LLMs) on research-level reasoning tasks.<n>CritPt consists of 71 composite research challenges designed to simulate full-scale research projects at the entry level.<n>We find that while current state-of-the-art LLMs show early promise on isolated checkpoints, they remain far from being able to reliably solve full research-scale challenges.
  arXiv  Detail & Related papers  (2025-09-30T17:34:03Z)
• ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition [67.26124739345332]
  Large language models (LLMs) have demonstrated potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined.<n>We introduce the first large-scale benchmark for evaluating LLMs with a near-sufficient set of sub-tasks of scientific discovery.<n>We develop an automated framework that extracts critical components - research questions, background surveys, inspirations, and hypotheses - from scientific papers.
  arXiv  Detail & Related papers  (2025-03-27T08:09:15Z)
• Autonomous LLM-driven research from data to human-verifiable research papers [0.0]
  We build an automation platform that guides interacting through complete stepwise process. In mode provided annotated data alone, datapaper raised hypotheses, designed plans, wrote and interpreted analysis codes, generated and interpreted results. We demonstrate potential for AI-driven acceleration of scientific discovery while enhancing traceability, transparency and verifiability.
  arXiv  Detail & Related papers  (2024-04-24T23:15:49Z)
• Mapping the Increasing Use of LLMs in Scientific Papers [99.67983375899719]
  We conduct the first systematic, large-scale analysis across 950,965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals. Our findings reveal a steady increase in LLM usage, with the largest and fastest growth observed in Computer Science papers.
  arXiv  Detail & Related papers  (2024-04-01T17:45:15Z)
• System for systematic literature review using multiple AI agents: Concept and an empirical evaluation [3.453564255183234]
  Systematic literature review ( SLR) is foundational to evidence-based research.<n>We introduce a novel multi-AI-agent system designed to fully automate SLRs.<n>We show how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
  arXiv  Detail & Related papers  (2024-03-13T10:27:52Z)

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.