Researchers · Interviewed at ICLR 2026

Naimeng Ye

Columbia University

ICLR 2026 in Rio de Janeiro. How to Make AI Agents Faster with Speculative Actions

ICLR 2026 · May 29, 2026 · 8 min

ICLR 2026 in Rio de Janeiro. How to Make AI Agents Faster with Speculative Actions

AI agents are powerful - but they could be painfully slow. Why? Because most agent workflows are fundamentally sequential: observe → reason → act → wait → repeat.

In this interview, Naimeng Ye explains Speculative Actions, a new framework that speeds up AI agents by introducing parallelism into agent execution. Inspired by speculative execution in CPUs and speculative decoding in LLMs, the method predicts likely future actions and starts executing them before the main agent finishes reasoning.

More from ICLR 2026

All event interviews →