From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Research

• URL: http://arxiv.org/abs/2603.13191v1
• Date: Fri, 13 Mar 2026 17:25:47 GMT
• Title: From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Research
• Abstract summary: We present QMatSuite, an open-source platform for AI-driven computational science.<n>QMatSuite stores findings with provenance, retrieves knowledge before new calculations, and in dedicated reflection sessions correct erroneous findings.<n>In benchmarks on a six-step quantum-mechanical simulation workflow, accumulated knowledge reduces reasoning overhead by 67% and improves accuracy from 47% to 3% deviation from literature.
• Score: 3.7193230342956056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models (LLMs) have transformed AI agents into proficient executors of computational materials science, performing a hundred simulations does not make a researcher. What distinguishes research from routine execution is the progressive accumulation of knowledge -- learning which approaches fail, recognizing patterns across systems, and applying understanding to new problems. However, the prevailing paradigm in AI-driven computational science treats each execution in isolation, largely discarding hard-won insights between runs. Here we present QMatSuite, an open-source platform closing this gap. Agents record findings with full provenance, retrieve knowledge before new calculations, and in dedicated reflection sessions correct erroneous findings and synthesize observations into cross-compound patterns. In benchmarks on a six-step quantum-mechanical simulation workflow, accumulated knowledge reduces reasoning overhead by 67% and improves accuracy from 47% to 3% deviation from literature -- and when transferred to an unfamiliar material, achieves 1% deviation with zero pipeline failures.

Related papers

• (Human) Attention Is (Still) All You Need: Human oversight makes AI-assisted social science reliable [15.442870614597451]
  We argue that the reliability of AI-assisted research depends not only on model capability, but also on how cognitive labour is structured between humans and machines.<n>We study this problem through Human-in-the-Loop Economic Research (HLER), a decision architecture based on pre-commitment, decision sequencing, accountability, and attention allocation.
  arXiv  Detail & Related papers  (2026-06-11T03:22:24Z)
• MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility [2.2969445973129123]
  We introduce MLReplicate, an end-to-end benchmark evaluating autonomous research systems on machine learning.<n>The benchmark was constructed from ICML 2025 papers reformulated into standardized input specifications and evaluated across 6 state-of-the-art research systems.<n>In contrast to automated reviews, human reviewers consistently identified methodological flaws, hallucinated experimental results, and failures across all systems.
  arXiv  Detail & Related papers  (2026-05-15T20:35:32Z)
• MDGYM: Benchmarking AI Agents on Molecular Simulations [25.37963706902467]
  We introduce MDGYM, a benchmark of 169 expert-curated MD simulations spanning LAMMPS and GROMACS.<n>We evaluate three agentic frameworks -- Claude Code, Codex, and OpenHands -- with four LLMs, and find that all perform poorly.<n>These failure modes are qualitatively distinct from those observed in general software engineering benchmarks, indicating that fluent code generation does not transfer to grounded physical reasoning.
  arXiv  Detail & Related papers  (2026-05-09T13:21:51Z)
• 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)
• Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows [203.3527268311731]
  We present an operational SGI definition grounded in the Practical Inquiry Model (PIM)<n>We operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning.<n>Our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.
  arXiv  Detail & Related papers  (2025-12-18T12:44:36Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• TusoAI: Agentic Optimization for Scientific Methods [16.268579802762247]
  Large language models (LLMs) have demonstrated strong capabilities in synthesizing literature, reasoning with empirical data, and generating domain-specific code.<n>Here, we introduce TusoAI, an agentic AI system that takes a scientific task description with an evaluation function.<n>TusoAI integrates domain knowledge into a knowledge tree representation and performs iterative, domain-specific optimization and model diagnosis.
  arXiv  Detail & Related papers  (2025-09-28T17:30:44Z)
• Operationalizing Serendipity: Multi-Agent AI Workflows for Enhanced Materials Characterization with Theory-in-the-Loop [0.0]
  SciLink is an open-source, multi-agent artificial intelligence framework designed to operationalize serendipity in materials research.<n>It creates a direct, automated link between experimental observation, novelty assessment, and theoretical simulations.<n>We show its application to atomic-resolution and hyperspectral data, its capacity to integrate real-time human expert guidance, and its ability to close the research loop.
  arXiv  Detail & Related papers  (2025-08-07T04:59:17Z)
• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
  o1-like models can emulate human-like long-time thinking during inference.<n>This paper presents the first comprehensive study on the prevalent issue of overthinking in these models.<n>We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
  arXiv  Detail & Related papers  (2024-12-30T18:55:12Z)
• The Return of Pseudosciences in Artificial Intelligence: Have Machine Learning and Deep Learning Forgotten Lessons from Statistics and History? [0.304585143845864]
  We argue that the designers and final users of these ML methods have forgotten a fundamental lesson from statistics.<n>We argue that current efforts to make AI models more ethical by merely reducing biases in the training data are insufficient.
  arXiv  Detail & Related papers  (2024-11-27T08:23:23Z)
• RESTOR: Knowledge Recovery in Machine Unlearning [71.75834077528305]
  Large language models trained on web-scale corpora can contain private or sensitive information.<n>Several machine unlearning algorithms have been proposed to eliminate the effect of such datapoints.<n>We propose the RESTOR framework for machine unlearning evaluation.
  arXiv  Detail & Related papers  (2024-10-31T20:54:35Z)
• Causal Discovery from Incomplete Data: A Deep Learning Approach [21.289342482087267]
  Imputated Causal Learning is proposed to perform iterative missing data imputation and causal structure discovery. We show that ICL can outperform state-of-the-art methods under different missing data mechanisms.
  arXiv  Detail & Related papers  (2020-01-15T14:28:21Z)

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.