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
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
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
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
This work introduces GameLogicBench, a benchmark of 72 gameplay-logic tasks in Godot projects, and compared versions of the benchmark evaluator built with and without validation using mutants.
Xin-Yu Che, Yun-Fei Ge, Shi-Hao Li et al.· arXiv.org· 2 citations
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.