collaborators

5 papers

cs.SE2026

Route-Align-Verify for Functional Correctness in Code Generation

Erxue Zhou, Jingxiang Meng, Aofan Liu

Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially for heterogeneous programming ta…

cs.AI2026

CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding

Aofan Liu, Jingxiang Meng, Fangxin Liu +1

Speculative decoding mitigates the latency of sequential generation in autoregressive Large Language Models (LLMs) by interleaving draft generation with target verification. Howeve…

cs.AI2026

TaPR: Test-Aware Policy Refinement for Feedback-Conditioned Code Generation

Aofan Liu, Jingxiang Meng, Fangxin Liu +1

Multi-turn code agents rely on execution feedback to repair incorrect programs, yet standard reinforcement learning paradigms optimize and evaluate policy performance primarily usi…

cs.CL2026

Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs

Aofan Liu, Jingxiang Meng

When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at tem…

cs.AI2026

Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs

Aofan Liu, Jingxiang Meng

Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains inconsistent across models. We r…