Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
Yi Xie, Siao Liu, Falong Fan +3
Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mod…
cs.LG2025
Enhancing Hierarchical Reinforcement Learning through Change Point Detection in Time Series
Hemanath Arumugam, Falong Fan, Bo Liu
Hierarchical Reinforcement Learning (HRL) enhances the scalability of decision-making in long-horizon tasks by introducing temporal abstraction through options-policies that span m…