activity
20242026
collaborators

6 papers

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…

cs.LG2025

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

Yong Lin, Shange Tang, Bohan Lyu +17

We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving. Built on the standard expert iteration and rein…

cs.SE2025

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Ori Press, Brandon Amos, Haoyu Zhao +21

Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming…

cs.AI2025

Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities

Haoyu Zhao, Yihan Geng, Shange Tang +5

LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems truly understand math…

cs.LG2025

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.CL2024

Can Models Learn Skill Composition from Examples?

Haoyu Zhao, Simran Kaur, Dingli Yu +2

As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not enco…