3 papers
cs.LG2026
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Xuekang Wang, Zhuoyuan Hao, Shuo Hou +3
Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models may exploit latent biases in t…
cs.CL2026
Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
Zhuoyuan Hao, Zhuo Li, Wu Li +3
Recent work improves reasoning in large reasoning models (LRMs) by test-time scaling through self-consistency and parallel thinking, adding generic "thinking tokens", or presenting…
cs.CE2025
Update Strategy for Channel Knowledge Map in Complex Environments
Ting Wang, Chiya Zhang, Chang Liu +4
The Channel Knowledge Map (CKM) maps position information to channel state information, leveraging environmental knowledge to reduce signaling overhead in sixth-generation networks…