2 papers
cs.AI2026
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Tarjei Paule Hage, Markus J. Buehler
Can reinforcement learning with hard, verifiable rewards teach a compact language model to reason about physics, or does it primarily learn to pattern-match toward correct answers?…
cs.AI2026
GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design
Isabella A. Stewart, Tarjei Paule Hage, Yu-Chuan Hsu +1
Large Language Models (LLMs) promise to accelerate discovery by reasoning across the expanding scientific landscape. Yet, the challenge is no longer access to information but conne…