10 papers
HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents
Jiangze Yan, Yi Shen, Wenjing Zhang +5
Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be re…
A Systematic Security Evaluation of OpenClaw and Its Variants
Yuhang Wang, Haichang Gao, Zhenxing Niu +4
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-on…
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
Wenjing Zhang, Jiangze Yan, Jieyun Huang +7
Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitation of rejection sampling. Standard methods treat th…
DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
Yi Shen, Jian Zhang, Jieyun Huang +7
Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating re…
MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance
Kaikai Zhao, Zhaoxiang Liu, Peng Wang +7
General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (IT…
Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu +11
DeepSeek-R1, renowned for its exceptional reasoning capabilities and open-source strategy, is significantly influencing the global artificial intelligence landscape. However, it ex…