20 citations · 53 across the 17 of their papers we have counts for
7 papers · 1 filter
Verifier-Grounded Agentic RL for Provably Correct Code
George Ma, Yuhao Zhang, Bing He +5
Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover. A program verifier instead decides w…
Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation
Hantao Yu, Sandy Han, Xiaoxue Han +6
On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the teacher is cond…
SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
George Ma, Benjamin Mikek, Haoyu Li +9
Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check correctness with held-out test suit…
Beyond Solver Verdicts: Generative Reward Models for Autoformalization
Vikash Singh, Debargha Ganguly, Aman Goel +5
Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict referenc…
Stratified Consistency Distillation for Natural Language Formalization
Zhichao Hou, Ferhat Erata, Joe Lilien +1
Neurosymbolic reasoning has shown promising success in addressing complex reasoning tasks by combining large language models (LLMs) and symbolic solvers. While this approach shows…
Fidelity Probes for Specification--Code Alignment
Ferhat Erata, Hao Zhou, Jun Huan +1
Software modernization often relies on natural-language specifications recovered from an existing implementation. Incorrect or missing requirements can lead to defects in the moder…
Learning How to Cube
Ferhat Erata, Sam Kouteili, Thanos Typaldos +4
Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transformer-based models can learn e…