6 papers
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
Wenpu Liu, Yuqi Xu, Weichu Xie +8
Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness, yet the collective…
Step-wise Rubric Rewards for LLM Reasoning
Weichu Xie, Haozhe Zhao, Wenpu Liu +15
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models, but rewards only final-answer correctness with no supervision ov…
RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback
Xiaoying Zhang, Zichen Liu, Yipeng Zhang +2
Standard reinforcement learning (RL) for large language model (LLM) agents primarily optimizes extrinsic task rewards, often favoring isolated task completion over continual adapta…
D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies
Sen Chen, Tong Zhao, Yi Bin +3
Developing intelligent agents capable of operating a wide range of Graphical User Interfaces (GUIs) with human-level proficiency is a key milestone on the path toward Artificial Ge…
DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents
Qi Li, Jianjun Xu, Pingtao Wei +8
With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deploy…
More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration
Xiaoyang Yuan, Yujuan Ding, Yi Bin +5
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods prima…