# Just-in-Time Memory curates raw agent traces when a new task arrives

DAIR.AI describes a Salesforce AI Research paper, Just-in-Time Memory, that keeps raw trajectories and writes a short memory payload only after the next task arrives. It reports gains of 16.2, 16.3 and 3.9 success-rate points over the strongest baseline on ALFWorld, WebShop and tau2-bench.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-17T15:12:00.000Z
Query date (America/Los_Angeles): 2026-11-17

HTML: https://didcodexreset.com/news/79c5966db1da49f59c7db1d2.html

Content language: en
Localization state: sameLanguage

Source: DAIR.AI · Published 9/26/2026, 05:50:28

DAIR.AI describes a Salesforce AI Research paper on agent memory called Just-in-Time Memory. Instead of summarizing each run when it ends, the method stores raw trajectories and decides what to extract from them when the next task arrives.

A curator reads the retrieved traces together with the new task and writes a short memory payload for that task. Because the payload is used immediately, the curator can be trained on whether that same task succeeds. DAIR.AI says that even an untrained curator matches or beats memory written at the end of a task.

On ALFWorld, WebShop and tau2-bench, DAIR.AI says Just-in-Time Memory beats the strongest baseline by 16.2, 16.3 and 3.9 success-rate points. The [Just-in-Time Memory paper](https://academy.dair.ai/papers/just-in-time-memory-learning-to-curate-task-adaptive-memory-for-llm-agents-2609.27334) is linked by DAIR.AI.

Tags: Just-in-Time Memory, Salesforce AI Research, agent memory, LLM agents

[View original post](https://x.com/dair_ai/status/2103828189407834259)
