6 papers
LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks
Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang +4
Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost. We i…
Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan +7
Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates int…
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
Chih-Hsuan, Yang, Tanwi Mallick +5
Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation…
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
Le Chen, Nuo Xu, Winson Chen +7
Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emer…
Implementing True MPI Sessions and Evaluating MPI Initialization Scalability
Hui Zhou, Kenneth Raffenetti, Yanfei Guo +2
Sessions is one of the major features introduced in the MPI-4 standard. It offers an alternative to the traditional world communicator model by allowing applications to construct c…
FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access
Aditya Tanikanti, Benoit Côté, Yanfei Guo +9
We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FI…