Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space
SiYuan Ma, Albert Gao, Chunzheng Zhu +6
Scientific discovery systems typically optimize experiments within a fixed hypothesis space. This creates a failure mode when all available candidates omit the same missing mechani…
cs.AI2026
CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
Siyuan Ma, Bo Gao, Zikai Xiao +6
Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over w…