3 papers
cs.LG2025
Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games
Xiaoqing Zhang, Huabin Zheng, Ang Lv +5
Large language models (LLMs) have been observed to suddenly exhibit advanced reasoning abilities during reinforcement learning (RL), resembling an ``aha moment'' triggered by simpl…
cs.SE2025
Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement
Xiaoqing Zhang, Yuhan Liu, Flood Sung +3
Code generation is crucial in software engineering for automating the coding process efficiently. While test-time computation methods show promise, they suffer from high latency du…
cs.LG2025
More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
Xiaoqing Zhang, Ang Lv, Yuhan Liu +6
Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as ICL demonstrations increase from a few to many, performanc…