4 papers
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Zhaoxin Yu, Qi Shen, Hengli Li +4
Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen. Exis…
Constraint-Enhanced Reinforcement Learning Based on Dynamic Decoupled Spherical Radial Squashing
Qijun Liao, Zhaoxin Yu, Jue Yang
When deploying reinforcement learning policies to physical robots, actuator rate constraints -- hard limits on how fast each joint can move per control step -- are unavoidable. The…
Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
Hengli Li, Chenxi Li, Tong Wu +8
Reasoning ability, a core component of human intelligence, continues to pose a significant challenge for Large Language Models (LLMs) in the pursuit of AGI. Although model performa…
BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
Hengli Li, Zhaoxin Yu, Qi Shen +8
Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a prin…