2 papers
cs.AR2026
OpenRDMA: A GPU-Native Multi-Path Reliable RDMA Transport Architecture
Ziheng Ji, Chunyu Liu, Weihao Peng +3
As the computing power density of large-scale AI clusters rises, network communication increasingly limits system performance. GPU-initiated communication requires low-overhead req…
cs.SE2026
Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
Saiyue Lyu, Jerrold Huang, Yunbei Zhang +4
Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We i…