Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks
Li Xia, Baoxun Wang
Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large. We study hybrid discovery systems t…
cs.LG2025
ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning
Zihao Feng, Xiaoxue Wang, Bowen Wu +4
While reinforcement learning (RL) is increasingly used for LLM-based tool learning, its efficiency is often hampered by an overabundance of simple samples that provide diminishing…