Peer-reviewer for 2nd Workshop on Efficient Reasoning

Serving as a peer reviewer for the 2nd Workshop on Efficient Reasoning, a workshop at COLM 2026, the Conference on Language Modeling. The workshop focuses on making reasoning models faster, cheaper, and more efficient, spanning datasets and evaluation, algorithms (fine-tuning, reinforcement learning, distillation, and compression), systems (long-context and multimodal inference, KV-cache and memory management, quantized execution), safety, and applications. It builds on its first edition at NeurIPS 2025. I am reviewing three submitted papers, assessing their methods, evidence, and contribution.