2 papers
cs.SE2026
RAT: RunAnyThing via Fully Automated Environment Configuration
Renhong Huang, Dongdong Hua, Yifei Sun +4
Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of configuring executable environments.…
cs.AI2026
PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game?
Dongdong Hua, Yifei Sun, Renhong Huang +3
Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require similar capabilities in realist…