4 papers
FactorLibrary: From Polynomials to Circuits via Recursive Subgoals
Rohan Pandey, Michael Ruofan Zeng, Weikun K. Zhang +5
Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We formulate it as a reinforcement…
AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models
Faqiang Qian, Kang An, Weikun Zhang +6
Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable…
Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
Ziliang Wang, Kang An, Xuhui Zheng +6
While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from t…
CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning
Weikun K. Zhang, Rohan Pandey, Bhaumik Mehta +5
Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and…