5 papers
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
Yifeng Ding, Hung Le, Songyang Han +5
Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challe…
Active Advantage-Aligned Online Reinforcement Learning with Offline Data
Xuefeng Liu, Hung T. C. Le, Siyu Chen +4
Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL le…
CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning
Minh Hoang Nguyen, Van Dai Do, Dung Nguyen +2
Large language model (LLM) agents-especially smaller, open-source models-often produce causally invalid or incoherent actions in collaborative tasks due to their reliance on surfac…
Reinforcement Learning for Causal Discovery without Acyclicity Constraints
Bao Duong, Hung Le, Biwei Huang +1
Recently, reinforcement learning (RL) has proved a promising alternative for conventional local heuristics in score-based approaches to learning directed acyclic causal graphs (DAG…
Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization
Georg Ziegner, Michael Choi, Hung Mac Chan Le +2
Multi-echelon inventory optimization (MEIO) is critical for effective supply chain management, but its inherent complexity can pose significant challenges. Heuristics are commonly…