Get started
Author

Jingxiang Meng

Observed name: Meng, Jingxiang
OpenAlex ID: A5144343237
Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs
2026 · Liu, Aofan, Meng, Jingxiang · arXiv (Cornell University) · 6
PDF
TaPR: Test-Aware Policy Refinement for Feedback-Conditioned Code Generation
2026 · Liu, Aofan, Meng, Jingxiang, et al. · arXiv (Cornell University) · 2
PDF
CheatBench: Measuring Reward Gaming in AI Agents
2026 · Phan, Long, Yang, Stephen K., et al. · arXiv (Cornell University) · 1
PDF
CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding
2026 · Liu, Aofan, Meng, Jingxiang, et al. · arXiv (Cornell University) · 1
PDF
Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
2026 · Liu, Aofan, Meng, Jingxiang · arXiv (Cornell University) · 1
PDF
REA: From Correct LLM Judgments to Safe Decision Delivery
2026 · Meng, Jingxiang, Liu, Aofan, et al. · arXiv (Cornell University)
PDF
Route-Align-Verify for Functional Correctness in Code Generation
2026 · Zhou, Erxue, Meng, Jingxiang, et al. · arXiv (Cornell University)
PDF
Works count: 7
Citation count: 11
H-index: 2
I10-index:
Year
Topic
Type