5 papers
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Haolong Qian, Xianliang Yang, Yinuo ma +6
Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher rewar…
Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning
Ling Zhang, Xianliang Yang, Juwon Yu +4
Fine-tuning large pretrained language models is a common approach for aligning them with human preferences, but noisy or off-target examples can dilute supervision. While small, we…
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
Xianliang Yang, Ling Zhang, Haolong Qian +2
Heuristic algorithms play a vital role in solving combinatorial optimization (CO) problems, yet traditional designs depend heavily on manual expertise and struggle to generalize ac…
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Yifan Xia, Xianliang Yang, Zichuan Liu +3
Recent advancements in solving large-scale traveling salesman problems (TSP) utilize the heatmap-guided Monte Carlo tree search (MCTS) paradigm, where machine learning (ML) models…
Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning
Zhihao Liu, Xianliang Yang, Zichuan Liu +7
Multi-agent reinforcement learning (MARL) is employed to develop autonomous agents that can learn to adopt cooperative or competitive strategies within complex environments. Howeve…