Moyan Li — accepted AI-conference papers

2026

CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems

Yifan Yu, Moyan Li, Shaoyuan Xu, Jinmiao Fu, Xinhai Hou, Fan Lai +1

ICML 2026poster

Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes error recognition particularly challenging. Minor errors can propagate across agents, escalating into task failures whil…

Cited by 0 Source ↗Scholar ↗

2026

CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization

Xinhai Hou, Shaoyuan Xu, Manan Biyani, Moyan Li, Jia Liu, Todd C Hollon +1

CVPR 2026

Agentic vision-language models are increasingly trained to "think with images" by calling image operations. However, we show that high final-answer accuracy often hides unfaithful visual reasoning: models may invoke tools on irrelevant regions or ignore tool outputs entirely, yet still guess the cor

Cited by 0 Source ↗code ↗Scholar ↗