New research from Meta.

(bookmark it)

It's on how to fix agents that forget previously made decisions.

It's well know that long-horizon agents keep forgetting decisions they already made. Meta researchers give this failure a name, behavioral state decay, where task facts, prior attempts, and open subgoals get buried in the context window or pushed past it, so they stop influencing the next action.

Their fix runs a separate memory agent alongside an unmodified action agent. It maintains a structured memory bank from the recent trajectory and decides, each step, whether to inject a memory-grounded reminder or stay silent. The module is plug-and-play with frontier agents and existing harnesses.

It lifts pass@1 for both weaker and stronger action agents on Terminal-Bench 2.0 and tau-squared-Bench.

Overall, they find that memory that actively surfaces the right fact at the right moment is a more useful primitive than passive retrieval that only fires when the agent thinks to ask.

Paper: https://arxiv.org/abs/2607.08716

Learn to build effective AI agents in our academy: https://academy.dair.ai/