1 citations · 2 across the 8 of their papers we have counts for
8 papers
TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code Generation
Minyu Chen, Sihao Wu, Ling-I Wu +5
Test-time scaling for code generation typically explores the solution space by sampling multiple programs from a fixed instruction. We study a complementary direction: instance-lev…
Schwarz: Solver-Aware Agentic Program Verification
Jingyu Ke, Ling-I Wu, Guoqiang Li
Agentic verification systems can often generate source-level specifications that look plausible, but plausibility is not enough: the verifier must still turn those specifications i…
Towards Automated Formal Verification of zkEVMs Using LLM-Guided Constraint Synthesis
Shichen Huang, Zhenghe Jiang, Yi Jiang +3
Zero-Knowledge Ethereum Virtual Machines (zkEVMs) secure Ethereum rollups by generating zero-knowledge proofs that guarantee off-chain execution correctness. However, subtle implem…
Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies
Minyu Chen, Song Qin, Ling-I Wu +2
LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly rely on delayed endpoint per…
DCE-LLM: Dead Code Elimination with Large Language Models
Minyu Chen, Guoqiang Li, Ling-I Wu +1
Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for…
ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge
Junyong Chen, Ling-I Wu, Minyu Chen +4
Automated Rule Checking (ARC) plays a crucial role in advancing the construction industry by addressing the laborious, inconsistent, and error-prone nature of traditional model rev…
Enhancing Automated Loop Invariant Generation for Complex Programs with Large Language Models
Ruibang Liu, Minyu Chen, Ling-I Wu +2
Automated program verification has always been an important component of building trustworthy software. While the analysis of real-world programs remains a theoretical challenge, t…
Can Language Models Pretend Solvers? Logic Code Simulation with LLMs
Minyu Chen, Guoqiang Li, Ling-I Wu +4
Transformer-based large language models (LLMs) have demonstrated significant potential in addressing logic problems. capitalizing on the great capabilities of LLMs for code-related…