Test-Time Computing

Sample Count Is Not Enough (arXiv:2609.19499): Why Candidate-Generation Strategy Matters for LLM Test-Time Scaling Energy and Performance
arXiv:2609.19499 — Self-consistency sample count N is not enough. At fixed N=8, generation schedules like 1×8 vs 8×1 can change A100 energy by about 4.6–4.9× and P95 latency by about 5.8–6.1×.
Mobina Kashaniyan
Posted Sep 16, 2026 Last updated Sep 17, 2026 Large Language Models, High-Performance Computing, Energy Efficiency, Test-Time Scaling, Research Summary
Interpretable Adaptive Sampling for LLM Test-Time Scaling and Test-Time Compute
Interpretable adaptive self-consistency for LLM test-time scaling. A fuzzy controller uses prompt complexity and model confidence to choose how many self-consistency samples each prompt receives.
Mobina Kashaniyan
Posted Aug 4, 2026 Large Language Models, Artificial Intelligence, LLM Reasoning, Test-Time Scaling, Research Summary

© 2026 Mobina Kashaniyan.