4 papers · 1 filter
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Sidi Yang, Chaofan Tao, Jierun Chen +11
Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficulty, harness design, and stude…
DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer
Ruoyu Wang, Junda Wu, Yu Xia +4
Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks. However, existing works ha…
Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation
Xinshu Li, Ruoyu Wang, Erdun Gao +2
Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundati…
Efficient and Generalizable Environmental Understanding for Visual Navigation
Ruoyu Wang, Xinshu Li, Chen Wang +1
Visual Navigation is a core task in Embodied AI, enabling agents to navigate complex environments toward given objectives. Across diverse settings within Navigation tasks, many nec…