2 papers
cs.AI2026
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
Benteng Chen, Weida Wang, Shufei Zhang +2
Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalt…
cs.LG2026
Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
Haodong Zhu, Yangyang Ren, Yanjing Li +6
Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While r…