Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning
Wei Yang, Qing Ping, Youzhi Luo +4
The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable an…
cs.AI2026
From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents
Xingyu Su, Abhishek Kumar, Qing Ping +5
On-policy self-distillation (OPSD) has become a popular recipe for post-training LLM agents. It supervises the agent model at the token level with a stronger teacher view of the sa…