11 papers
Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics
Xiyu Zhai, Xinyi Chen, Yiping Wang +3
We present a dependent-type-based prover designed around the way LLMs (and humans) tend to write mathematics, complementing existing systems such as Lean and Rocq. Its core design…
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
Zhiyuan Zeng, Hamish Ivison, Yiping Wang +14
We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide alg…
Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
Zeyi Huang, Xuehai He, LiLiang Ren +8
We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as…
Spurious Rewards: Rethinking Training Signals in RLVR
Rulin Shao, Shuyue Stella Li, Rui Xin +11
We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little,…
ThetaEvolve: Test-time Learning on Open Problems
Yiping Wang, Shao-Rong Su, Zhiyuan Zeng +13
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to im…
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Yiping Wang, Qing Yang, Zhiyuan Zeng +11
We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language…