7 papers
PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
Yu Li, Guangfeng Cai, Shengtian Yang +5
Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-step tool pl…
Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning
Siyu Gong, Linan Yue, Weibo Gao +4
Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to solve complex tasks by interacting with external tools, yet existing approaches depend on high-quality synth…
The Final Layer Holds the Key: A Unified and Efficient GNN Calibration Framework
Jincheng Huang, Jie Xu, Xiaoshuang Shi +3
Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness on graph-based tasks. However, their predictive confidence is often miscalibrated, typically exhibiting unde…
Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling
Zongqian Wu, Baoduo Xu, Tianyu Li +3
Test-time scaling (TTS) has been shown to improve the performance of large language models (LLMs) by sampling and aggregating diverse reasoning paths. However, existing research ha…
Rethinking Chain-of-Thought from the Perspective of Self-Training
Zongqian Wu, Baoduo Xu, Ruochen Cui +3
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-trainin…
Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
Jincheng Huang, Yujie Mo, Xiaoshuang Shi +2
The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to reach more unlabeled neighbors, thereby increasing the utilization of labels…