2 papers
cs.CL2026
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Guibin Zhang, Leo Lu, Fangzhou Xie +15
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can domi…
cs.HC2026
IF:CARGO: LLM-Based Semantic Compilation for Al-Native Rule Programming Games
Ting-Chen Hsu, Lianye Zhang, Jiangxu Lin +3
This case study presents IF: CARGO, an experimental puzzle game that uses a large language model as a semantic compiler rather than an autonomous game-playing agent. Players author…