4 papers · 1 filter
Belief-Trajectory Energy: Measuring the Path to a Prediction
Jiahao Ying, Wei Tang, Boxian Ai +7
Large language models (LLMs) progressively revise their predictions across Transformer layers, yet we typically observe only the final output, discarding the trajectory through whi…
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
Jiahao Ying, Boxian Ai, Wei Tang +2
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-…
In-Context Learning Operates as Concept Subspace Learning
Wei Tang, Xinyan Jiang, Fakhri Karray +1
Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…
SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning
Chenyi Li, Yuan Zhang, Bo Wang +4
Reinforcement learning with verifiable rewards has shown notable effectiveness in enhancing large language models (LLMs) reasoning performance, especially in mathematics tasks. How…