7 papers
REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
Keer Lu, Liwei Chen, Guoqing Jiang +3
Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons. However, due to their finite context window, LLMs cannot retain all past inte…
Med-R: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning
Keer Lu, Zheng Liang, Youquan Li +8
In medical scenarios, effectively retrieving external knowledge and leveraging it for rigorous logical reasoning is of significant importance. Despite their potential, existing wor…
PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning
Keer Lu, Chong Chen, Xili Wang +3
Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces challenges when deploying LLMs in age…
Med-R: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine
Keer Lu, Zheng Liang, Da Pan +6
Large Language Models (LLMs) have exhibited remarkable capabilities in clinical scenarios. Despite their potential, existing works face challenges when applying LLMs to medical set…
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Keer Lu, Keshi Zhao, Zhuoran Zhang +8
As demonstrated by the proprietary Large Language Models (LLMs) such as GPT and Claude series, LLMs have the potential to achieve remarkable proficiency across a wide range of doma…
Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
Mingyang Chen, Haoze Sun, Tianpeng Li +7
Large Language Models (LLMs) have exhibited significant potential in performing diverse tasks, including the ability to call functions or use external tools to enhance their perfor…