5 citations · 21 across the 14 of their papers we have counts for
15 papers
ProgAgent: Learning Tool Orchestration through Programmatic Training
Hao Li, Keqing He, Longtao Zheng +4
Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where the mode…
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
Zhiyi Lyu, Yewen Li, Longtao Zheng +7
LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundamentally difficult: real-world…
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Lang Feng, Longtao Zheng, Shuo He +2
Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. I…
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Wei Liu, Jiawei Xu, Yingru Li +4
High-quality kernel is critical for scalable AI systems, and enabling LLMs to generate such code would advance AI development. However, training LLMs for this task requires suffici…
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
Yingru Li, Jiawei Xu, Ziniu Li +10
Reinforcement Learning (RL) for Large Language Models (LLMs) often suffers from training collapse in long-horizon tasks due to exploding gradient variance. To mitigate this, a base…
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Zhenghai Xue, Longtao Zheng, Qian Liu +4
Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However…
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
Lang Feng, Weihao Tan, Zhiyi Lyu +5
Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic…
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
Longtao Zheng, Yifan Zhang, Hanzhong Guo +6
Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, ma…
AgentStudio: A Toolkit for Building General Virtual Agents
Longtao Zheng, Zhiyuan Huang, Zhenghai Xue +3
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments a…
Cradle: Empowering Foundation Agents Towards General Computer Control
Weihao Tan, Wentao Zhang, Xinrun Xu +25
Despite the success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encaps…
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
Wentao Zhang, Lingxuan Zhao, Haochong Xia +10
Financial trading is a crucial component of the markets, informed by a multimodal information landscape encompassing news, prices, and Kline charts, and encompasses diverse tasks s…
True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning
Weihao Tan, Wentao Zhang, Shanqi Liu +3
Despite the impressive performance across numerous tasks, large language models (LLMs) often fail in solving simple decision-making tasks due to the misalignment of the knowledge i…
Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification
Dong Xing, Pengjie Gu, Qian Zheng +5
Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation o…
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
Longtao Zheng, Rundong Wang, Xinrun Wang +1
Building agents with large language models (LLMs) for computer control is a burgeoning research area, where the agent receives computer states and performs actions to complete comp…
Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning
Rundong Wang, Longtao Zheng, Wei Qiu +7
Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from s…