3 papers
cs.LG2026
Principle-Evolvable Scientific Discovery via Uncertainty Minimization
Yingming Pu, Tao Lin, Hongyu Chen
Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencies due to adherence to fixed initial pr…
cs.LG2026
PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration
Yingming Pu, Tao Lin, Hongyu Chen
Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discov…
cond-mat.mtrl-sci2025
Mechanisms of Matter: Language Inferential Benchmark on Physicochemical Hypothesis in Materials Synthesis
Yingming Pu, Tao Lin, Hongyu Chen
The capacity of Large Language Models (LLMs) to generate valid scientific hypotheses for materials synthesis remains largely unquantified, hindered by the absence of benchmarks pro…