3 papers
cs.LG2026
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Zhi Zheng, Rongsheng Chen, Yunpeng Ba +3
Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rew…
cs.AI2026
SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
Rongsheng Chen, Changliang Zhou, Canhong Yu +4
Generalist neural routing solvers have shown great potential in solving diverse vehicle routing problems (VRPs) with a unified model. However, existing solvers are typically limite…
cs.AI2026
Rethinking Constraint Awareness for Efficient State Embedding of Neural Routing Solver
Canhong Yu, Changliang Zhou, Rongsheng Chen +2
Heavy-Encoder-Light-Decoder (HELD) neural routing solvers have emerged as a promising paradigm due to their broad applicability across multiple vehicle routing problems (VRPs). How…