Article

TokenWorth: Learning which memories are worth keeping under resource constraints

The paper proposes TokenWorth, a lightweight online memory framework that learns query-relevant memory value from sparse execution feedback and applies it consistently to memory retrieval and bounded memory management. Across three LifelongAgentBench environments and in both local and API-based deployments, TokenWorth achieves the highest task success rate among the evaluated methods while using the fewest output tokens. The code is publicly available at https://github.com/AIGNLAI/TokenWorth.

Part of the event: Proposes the TokenWorth online memory framework

This page provides a summary and source link only.