Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution
cond-mat.mtrl-sci, cond-mat.mes-hall, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/LAMM-MIT/MARS
Sources
- AI for Science: An Emerging Agenda
- Finetuned Language Models Are Zero-Shot Learners
- ReAct: Synergizing Reasoning and Acting in Language Models
- A Survey on Large Language Model based Autonomous Agents
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- LLM Multi-Agent Systems: Challenges and Open Problems
- Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles
- Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation
- Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoning
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange
- SwarmWorld: Stigmergic technological evolution in societies of language-model agents
- Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning
- From Text to Insight: Large Language Models for Materials Science Data Extraction
- Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Framework
- Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
- Higher-Order Knowledge Representations for Agentic Scientific Reasoning
- GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design
- gpt-oss-120b & gpt-oss-20b Model Card
- CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning
Related papers
- Mode-selective electron-phonon coupling drives charge density waves in the kagome metals YRu 3 Si 2 and LaRu 3 Si 2
- Restoring the Surface Magnetic Gap in MnBi 2 Te 4
- ATLAS: A Foundation Neural Sampler for Amorphous Materials
- A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics
- Nonlinear dynamics in magnonic Fabry-P' e rot resonators: Low-power neuron-like activation and transmission suppression
- AES-Debye: an Accurate, Efficient, and Scalable Engine for Debye Scattering Calculations