7 papers
When Does Muon Help Agentic Reinforcement Learning?
Kai Ruan, Jinghao Lin, Zihe Huang +4
Muon is competitive with AdamW in large-scale pre-training, but its operating regime in reinforcement-learning post-training remains unclear. We map this regime on ALFWorld, a spar…
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Kai Ruan, Zihe Huang, Ziqi Zhou +4
The paper proposes using lightweight linear probes on hidden states of large language model agents to predict failures early and abort doomed episodes, achieving large compute savi…
PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination
Xuan Wang, Kai Ruan, Jiayi Han +2
Audio-driven bimanual piano motion generation requires precise modeling of complex musical structures and dynamic cross-hand coordination. However, existing methods often rely on a…
Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context
Kai Ruan, Xuan Wang, Jixiang Hong +3
While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately extracting key find…
X-MoGen: Unified Motion Generation across Humans and Animals
Xuan Wang, Kai Ruan, Liyang Qian +3
Text-driven motion generation has attracted increasing attention due to its broad applications in virtual reality, animation, and robotics. While existing methods typically model h…
Benchmarking LLMs' Swarm intelligence
Kai Ruan, Mowen Huang, Ji-Rong Wen +1
Large Language Models (LLMs) show potential for complex reasoning, yet their capacity for emergent coordination in Multi-Agent Systems (MAS) when operating under strict swarm-like…