10 papers
DR-Arena: an Automated Evaluation Framework for Deep Research Agents
Yiwen Gao, Ruochen Zhao, Yang Deng +1
As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, reliable evaluation of their task p…
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Xiangyi Li, Yimin Liu, Wenbo Chen +75
Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to m…
ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network
Junzhou Li, Manqi Zhao, Yilin Gao +4
Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from exc…
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference
Fuliang Liu, Xue Li, Ketai Zhao +7
Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accur…
Bridging the Knowledge-Action Gap by Evaluating LLMs in Dynamic Dental Clinical Scenarios
Hongyang Ma, Tiantian Gu, Huaiyuan Sun +9
The transition of Large Language Models (LLMs) from passive knowledge retrievers to autonomous clinical agents demands a shift in evaluation-from static accuracy to dynamic behavio…
Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models
Zizhi Chen, Yizhen Gao, Minghao Han +4
Multimodal biomedical Vision-Language Models (VLMs) exhibit immense potential in the field of Continual Learning (CL). However, they confront a core dilemma: how to preserve fine-g…