6 papers
MAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning
Xinping Wang, Jie Ma, Rui Xing +6
Mathematical reasoning is a fundamental capability for educational applications of Large Language Models (LLMs), where reliable problem solving requires not only correct answers bu…
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
Shihao Qi, Jie Ma, Rui Xing +15
LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, t…
Is AI Ready for Multimodal Hate Speech Detection? A Comprehensive Dataset and Benchmark Evaluation
Rui Xing, Qi Chai, Jie Ma +5
Hate speech online targets individuals or groups based on identity attributes and spreads rapidly, posing serious social risks. Memes, which combine images and text, have emerged a…
From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision
Jie Ma, Shihao Qi, Rui Xing +4
The quality of process data plays a key role in training a Process Reward Model (PRM), which can enhance the complex mathematical reasoning capability of large language models. Exi…
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
Jie Ma, Ning Qu, Zhitao Gao +8
Knowledge graph-based retrieval-augmented generation seeks to mitigate hallucinations in Large Language Models (LLMs) caused by insufficient or outdated knowledge. However, existin…
QSketch: An Efficient Sketch for Weighted Cardinality Estimation in Streams
Yiyan Qi, Rundong Li, Pinghui Wang +2
Estimating cardinality, i.e., the number of distinct elements, of a data stream is a fundamental problem in areas like databases, computer networks, and information retrieval. This…