Skip to content

Author

Xin-Yu Che

We have 6 of 9 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.

#artificial intelligence Preprint Oct 2026

Rome Wasn't Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents

Training language-model agents to play long-horizon strategy games is hard because deterministic feedback is sparse and often arrives only at the end of a game. In-game scores can offer dense signals, but they do not reliably predict future outcomes: in 8-68% of position pairs across eight strategy games, the higher-sc...

Yan-Chen Liu, Xin-Yu Che, Brihi Joshi et al. · 0 citations
Preprint Oct 2026

From Code to Playable Systems: CEGame-Bench for Long-Horizon Game Creation Agents

CEGame-Bench is presented, the first long-horizon benchmark for complete-game creation across five production engines: Defold, Godot, Roblox Studio, Unity, and Unreal Engine, and Game Completion Boost, an agent skill for requirement-driven playtesting and repair that raises the execution-based score of three models.

Zi-Xuan Dong, Yang-Hai Wang, Han-Yan Bian et al. · 3 citations
#artificial intelligence Review Oct 2026

Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of use, which a successful task attempt can leave untested. We introduce Socratic Skill Learning (SSL), which interleaves expert teaching with Student pr...

Le-Tian Zhu, Han Li, Yi-Fan Yao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training

This work replaces true next-observation targets with in-distribution mismatched observations and introduces a setting that replaces prediction-based rewards with independent random signals, which expands task coverage even when the reward carries no environment information.

Xin-Yu Che, Hang Yan, Yan-Chen Liu et al. · 0 citations
Preprint Aug 2026

QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents

A structured memory framework for query-conditioned user-state inference for long-term personalization that achieves state-of-the-art performance on both PersonaMem and KnowU-Bench, demonstrating the effectiveness of query-conditioned user-state inference for long-term personalization.

Heng Wang, Yifei Li, Lingling Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.