Author

Cao Liu

Observed name: Liu, Cao

Institutions: University of Chinese Academy of Sciences, Meituan (China)

Observed institutions: University of Chinese Academy of Sciences, Meituan (China)

OpenAlex ID: A5127888391

ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning

2026 · Zhou, Shuaiyu, Yue, Fengpeng, et al. · arXiv (Cornell University)

STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios

2026 · Liang, Sirui, Yu, Bohan, et al. · arXiv (Cornell University)

Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG

2026 · Wang, Xihang, Wang, Zihan, et al. · arXiv (Cornell University)

Factorized Latent Reasoning for LLM-based Recommendation

2026 · Gao, Tianqi, Huang, Chengkai, et al. · arXiv (Cornell University)

Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation

2026 · Jiang, Yubo, Yang, Xin, et al. · arXiv (Cornell University)

V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization

2026 · Jiang, Yubo, An, Yitong, et al. · arXiv (Cornell University)

Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding

2026 · Jiang, Yubo, An, Yitong, et al. · arXiv (Cornell University)

AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction

2026 · Yang, Jiashu, Zhang, Chi, et al. · arXiv (Cornell University)

Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems

2026 · Zhang, Yuzhe, Liu, Feiran, et al. · arXiv (Cornell University)

Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO

2026 · Yang, Xin, Li, Letian, et al. · arXiv (Cornell University)

TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios

2026 · Shen, Yuanzhe, Huang, Zisu, et al. · arXiv (Cornell University)

Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue

2026 · Jia, Yuhang, Liu, Pei, et al. · arXiv (Cornell University)

When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems

2026 · Xin Yang, Junhao Wang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

Works count: 13

Citation count:

H-index:

I10-index: