AI.info

Xingshan Zeng

Explore Xingshan Zeng on AI.info.

• What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
• EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents