2 papers
cs.AI2026
AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction
Rui Zou, Yutao Zhu, Mengqi Wei +1
Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challenging. Existing representativ…
cs.AI2025
Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis
Rui Zou, Mengqi Wei, Yutao Zhu +3
Large Language Models (LLMs) excel in reasoning and generation across domains, but still struggle with identifying and diagnosing complex errors. This stems mainly from training ob…