4 papers · 1 filter
Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
Fiona Y. Wang, Markus J. Buehler
Scientific discovery is not only answer generation but revision of the representational regime in which evidence, artifacts, operations, and verifiers are typed. We develop a categ…
Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence
Fiona Y. Wong, Markus J. Buehler
Scientific evidence often spans instruments, databases, and disciplines, so no single source records the full phenomenon. This makes it difficult to determine when coordinated AI a…
Recursive Multi-Agent Systems
Jiaru Zou, Rui Pan, Ruizhong Qiu +8
Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend…
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?…