4 citations · 9 across the 12 of their papers we have counts for
4 papers · 1 filter
Spurious Advantage Hidden in GRPO
Jiamian Wang, Samyadeep Basu, Koustava Goswami +2
Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifiable rewards, where its advantage estimator assigns each rollout a magnitude from…
Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving
Meibo Hu, Jiamian Wang, Pichao Wang +1
Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs and high-level navigation in…
HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement Learning
Haowei Liu, Jiamian Wang, Hsin-Tai Wu +2
Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed. We introduce Hin…
DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
Jiamian Wang, Ruiyi Zhang, Tong Yu +5
Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training envir…