PM-Bench: New Benchmark Evaluates Prospective Memory in LLM Agents

Jul 15, 2026

Researchers have introduced PM-Bench, a text-based benchmark inspired by cognitive science to assess prospective memory in large language model (LLM) agents. In this benchmark, agents must remember and execute delayed intentions while performing ongoing tasks over a simulated seven-day week. The best-performing agent, GPT-5.4, achieved only a 65.1% F1 score, indicating that prospective memory remains a significant challenge for current LLMs.

Why it matters: PM-Bench exposes a key limitation in LLM agents' ability to reliably manage and execute future tasks, which is crucial for their deployment in real-world autonomous applications.

Full story at: arXiv AI/ML ↗