7 papers
VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track
Wenming Tu, Jian Gao, Yanru Huo +9
Audio reasoning requires multi-step, evidence-grounded inference over temporally dynamic and acoustically mixed signals, exceeding conventional perception tasks such as ASR or capt…
LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models
Jian Gao, Richeng Xuan, Zhaolu Kang +9
The rapid advancement of large language models (LLMs) has not been matched by their evaluation in low-resource languages, especially Southeast Asian languages like Lao. To fill thi…
Reinforcement World Model Learning for LLM-based Agents
Xiao Yu, Baolin Peng, Ruize Xu +6
Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and ada…
Dynamic Role Assignment for Multi-Agent Debate
Miao Zhang, Junsik Kim, Siyuan Xiang +2
Multi-agent large language model (LLM) and vision-language model (VLM) debate systems employ specialized roles for complex problem-solving, yet model specializations are not levera…
Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency
Haoran Wang, Maryam Khalid, Qiong Wu +2
Large language models (LLMs) are increasingly used in applications requiring factual accuracy, yet their outputs often contain hallucinated responses. While fact-checking can mitig…
SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models
Xiangyu Dong, Haoran Zhao, Jiang Gao +5
Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities i…