Memory-Augmented Speculative Execution Accelerates LLM Agents Losslessly

Jul 15, 2026

A new method equips speculative execution in LLM agents with three online memory systems—a contrastive transition table, episodic memory, and confusion tracker—to improve prediction quality by learning from past agent trajectories. The approach achieves 19–39% relative accuracy improvement on action prediction and up to 2.5× increase on observation prediction tasks, with gains increasing as memory accumulates. All speculation occurs during idle time, resulting in no added wall-clock cost and preserving identical agent trajectories compared to non-speculative execution.

Why it matters: This work demonstrates a way for LLM agents to learn from experience and improve efficiency without sacrificing correctness, potentially advancing the deployment of faster and more capable agentic systems.

Full story at: arXiv Machine Learning ↗