Lune

ICML2026Top-tier venue

MADE: Benchmark Environments for Closed-Loop Materials Discovery

Shreshth Malik, Tiarnan Doherty, Panagiotis Tigas, Muhammed Razzak, Stephen Roberts, Aron Walsh, Yarin Gal

Abstract

Existing benchmarks for computational materials discovery primarily evaluate static predictive tasks or isolated computational sub-tasks. While valuable, these evaluations neglect the inherently iterative and adaptive nature of scientific discovery. We introduce MAterials Discovery Environments (MADE), a novel framework for benchmarking end-to-end autonomous materials discovery pipelines. MADE simulates closedloop discovery campaigns in which an agent or algorithm proposes, evaluates, and refines candidate materials under a constrained oracle budget, capturing the sequential and resource-limited nature of real discovery workflows. We formalize discovery as a search for thermodynamically stable compounds relative to a given convex hull, and evaluate efficacy and efficiency via comparison to baseline algorithms. The framework is flexible; users can compose discovery agents from interchangeable components such as generative models, filters, and planners, enabling the study of arbitrary workflows ranging from fixed pipelines to fully agentic systems with tool use and adaptive decision making. We demonstrate this by conducting systematic experiments across a family of systems, enabling ablation of components in discovery pipelines, and comparison of how methods scale with system complexity.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Large Language Models to Enhance Bayesian Optimization cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • ReAct: Synergizing Reasoning and Acting in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on5

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Crystal Diffusion Variational Autoencoder for Periodic Material GenerationTian Xie, Xiang Fu, Octavian-Eugen Ganea, Regina Barzilay et al.ICLR 2022 · 394 citations
  3. Large Language Models to Enhance Bayesian OptimizationTennison Liu, Nicolás Astorga, Nabeel Seedat, Mihaela van der SchaarICLR 2024 · 143 citations
  4. Resolving the data ambiguity for periodic crystalsDaniel Widdowson, Vitaliy KurlinNeurIPS 2022 · 62 citations
  5. ReAct: Synergizing Reasoning and Acting in Language ModelsShunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du et al.ICLR 2023

Related papers

  1. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific DiscoveryZiru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang et al.ICLR 2025 · 6 citations
  2. LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge RetrievalYuan Chiang, Elvis Hsieh, Chia-Hong Chou, Janosh RiebesellEMNLP 2025 · 7 citations
  3. Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for AgentsNolan Koblischke, Hyunseok Jang, Kristen Menou, Mohamad Ali-DibICML 2025
  4. Procedural Generation Of Algorithm Discovery Tasks in Machine LearningAlexander D. Goldie, Zilin Wang, Adrian Hayler, Deepak Nathani et al.ICML 2026 · 2 citations
  5. DSGym: A Standardized and Holistic Framework for Evaluating and Training Data Science AgentsFan Nie, Junlin Wang, Harper Hua, Federico Bianchi et al.ICML 2026 · 12 citations
Dusk over the sea between two cliffs drawn in fine vertical lines