← Search

Gerald Friedland

2 accepted papers

2026

Self-Aligned Reward: Towards Effective and Efficient Reasoners

ICLR 2026poster

Reinforcement learning with verifiable rewards has significantly advanced reasoning with large language models (LLMs) in domains such as mathematics and logic. However, verifiable signals provide only coarse-grained or binary correctness feedback. This limitation results in inefficiencies like overl…

Cited by 0SourceScholar