100 citations · 176 across the 12 of their papers we have counts for
4 papers · 1 filter
PROOF-Gen: From Optimized Data to Better Distillation
Anh Ta, Junjie Zhu, Shahin Shayandeh
Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Post-training pipelines that d…
Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents
Anh Ta, Junjie Zhu, Shahin Shayandeh
Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the act…
Robust Conversational AI with Grounded Text Generation
Jianfeng Gao, Baolin Peng, Chunyuan Li +4
This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale Transf…
Guided Dialog Policy Learning without Adversarial Learning in the Loop
Ziming Li, Sungjin Lee, Baolin Peng +5
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable…