7 papers
EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization
Xinbang Dai, Zheyu Xin, Huikang Hu +7
Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such as fast-slow thinking switch…
KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering
Yike Wu, Nan Hu, Guilin Qi +11
Recent research has explored the integration of knowledge graphs (KGs) with large language models (LLMs) to enhance their performance on downstream knowledge-intensive tasks, parti…
GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces
Xinyu Geng, Yanjing Xiao, Yuyang Zhang +5
Deep research agents integrate fragmented evidence through multi-step tool use. BrowseComp offers a text-only testbed for such agents, but existing multimodal benchmarks rarely req…
Cross-modal Fuzzy Alignment Network for Text-Aerial Person Retrieval and A Large-scale Benchmark
Yifei Deng, Chenglong Li, Yuyang Zhang +2
Text-aerial person retrieval aims to identify targets in UAV-captured images from eyewitness descriptions, supporting intelligent transportation and public security applications. C…
ELAIPBench: A Benchmark for Expert-Level Artificial Intelligence Paper Understanding
Xinbang Dai, Huikang Hu, Yongrui Chen +6
While large language models (LLMs) excel at many domain-specific tasks, their ability to deeply comprehend and reason about full-length academic papers remains underexplored. Exist…
Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
Yihong Tang, Kehai Chen, Liang Yue +11
With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence.…