3 papers
cs.CL2026
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Xiaoyu Tian, Haotian Wang, Shuaiting Chen +12
Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing meth…
cs.AI2026
CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
Huan-ang Gao, Zikang Zhang, Tianwei Luo +9
Large Language Model (LLM) agents, while proficient in the digital realm, face a significant gap in physical-world deployment due to the challenge of forming and maintaining a robu…
cs.AI2025
Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use
Anna Goldie, Azalia Mirhoseini, Hao Zhou +2
Reinforcement learning has been shown to improve the performance of large language models. However, traditional approaches like RLHF or RLAIF treat the problem as single-step. As f…