collaborators

11 papers

cs.LG2026

Latent On-Policy Self-Distillation

Guibin Zhang, Jiayang Lyu, Ran Sun +4

Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effecti…

cs.LG2026

SuperThoughts: Reasoning Tokens in Superposition

Zheyang Xiong, Shivam Garg, Max Yu +4

Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation. While recent works explore reasoning in cont…

cs.SE2026

AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms

Haoyu Zhao, Ziran Yang, Jiawei Li +6

Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a unified methodology for cross-paradig…

cs.LG2026

Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set

Yikai Wu, Haoyu Zhao, Sanjeev Arora

AI methods, such as generative models and reinforcement learning, have recently been applied to combinatorial optimization (CO) problems, especially NP-hard ones. This paper compar…

cs.SE2026

Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification

Zenan Li, Ziran Yang, Deyuan He +7

Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations satisfy specifications requires constr…

cs.CL2026

Contextual Drag: How Errors in the Context Affect LLM Reasoning

Yun Cheng, Xingyu Zhu, Haoyu Zhao +1

Central to many self-improvement pipelines for large language models (LLMs) is the assumption that models can improve by reflecting on past mistakes. We study a phenomenon termed c…