10 papers
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
Zhisong Qiu, Shuofei Qiao, Kewei Xu +4
Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs) within static domains such as mathematics. Ho…
Exploring Autonomous Agentic Data Engineering for Model Specialization
Yujie Luo, Xiangyuan Ru, Jingsheng Zheng +10
Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data…
Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation
Kewei Xu, Junbo Qi, Yanyan Zou +3
Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement.…
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
Kewei Xu, Xiaoben Lu, Shuofei Qiao +4
Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical…
From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
Ke Xu, Yuhao Wang, Yu Wang
Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus…
AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
Yixiang Zhang, Xinhao Deng, Jiaqing Wu +3
Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileg…