16 papers
Start Classifying: Categorical Critics for LLM Reinforcement Learning
Zhijian Zhou, Long Li, Xuan Zhang +7
Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets. Although scalar MSE is stat…
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Tencent WorkBuddy Bench Team, Siqi Cai, Shaopeng Chen +35
We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model lea…
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
Xuan Zhang, Zhijian Zhou, Lingfeng Qiao +6
Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans wh…
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning
Hongjun Wang, Wei Liu, Weibo Gu +2
Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, suc…
SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents
Shaofei Cai, Yulei Qin, Haojia Lin +10
Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verif…
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Yuchen Shi, Yuzheng Cai, Siqi Cai +15
Existing Large Language Model (LLM) agent frameworks face two significant challenges: high configuration costs and static capabilities. Building a high-quality agent often requires…