Author

Yi-Xiong Chen

h-index 6 View on Semantic Scholar

We have 2 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories

This work proposes Agentic-DPO, a lightweight offline agent policy optimization method that turns expert trajectories into state-conditioned preference supervision, and introduces Policy-Preserving Augmentation (PPA), which renders the same latent trajectory under multiple schemas while keeping the expert policy fixed.

Yi-Xiong Chen, A. Yuille · arXiv.org · 3 citations

Jul 2026

The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory

Enter--Propagation--Recovery (E-P-R), a trajectory-level framework that asks where memory first changes an action, whether that change carries forward, and whether the agent can recover after leaving a correct path is proposed, to diagnose how models consume retrieved memory across a multi-step action trajectory.

Yi-Xiong Chen, Xin-Yi Bai, Alan L. Yuille · arXiv.org · 0 citations