Guiyang Hou

Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as pseudo-labels. However, we identify a critical failure mode: as training maximizes self-consistency, output diversity...

Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains, where the agent must continuously interact with environments and process observation-action interleaved trajectories, remains largely u...

Theory of Mind (ToM), the ability to infer others’ mental states from behavior, is pivotal for developing machines with human-level social intelligence. Existing methods endowing LLMs with ToM fall into two paradigms: training-free methods and those repurposing ToM evaluation benchmarks as traini...