Oral Presentations I (4 papers)

All times PDT, October 9, 2026.

09:15–09:30 — Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows — Hardy Chen

09:30–09:45 — Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter Calibration — Eliya Habba

09:45–10:00 — LLM-as-a-Verifier: A General-Purpose Verification Framework — Jacky Kwok

10:00–10:15 — Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference — Joel Persson