Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
AgentWorld: A Data Factory for Training LLM Agents from Multi-Turn Interactions
Daoyu Wang, Mingyue Cheng, Qingchuan Li +4
Training LLMs to act as capable agents requires learning from multi-turn interactions with environments. However, multi-turn interaction trajectories generated by heterogeneous age…
cs.LG2026
SocraticPO: Policy Optimization via Interactive Guidance
Zirui Liu, Tingyue Pan, Jie Ouyang +8
Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization dir…
cs.LG2026
From Path Signatures to Sequential Modeling: Incremental Signature Contributions for Offline RL
Ziyi Zhao, Qingchuan Li, Yuxuan Xu
Path signatures embed trajectories into tensor algebra and constitute a universal, non-parametric representation of paths; however, in the standard form, they collapse temporal str…