Paper page - Remembering Has a Price: Learning Memory Worth under Resource Constraints

Source: https://huggingface.co/papers/2610.26453

Abstract

TokenWorth is a lightweight online memory framework that learns which past experiences are worth retaining and reusing under tight resource constraints, improving lifelong agent success while reducing token usage.

Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such stringent joint constraints, we find that existinglifelong-memorymethods can become ineffective, with several sophisticated approaches offering little advantage over simple retrieval or even no-memory agents. This reveals a more fundamental problem: resource scarcity makes each memory decision more consequential. When only a small amount of past experience can be retained or reused and opportunities for reasoning and recovery are limited, retrieving a relevant but ineffective memory can consume scarce context and hinder downstream execution. The key challenge is therefore not simply to retrieve relevant experience, but to determine which experiences are actually worth retaining and reusing. To address this challenge, we proposeTokenWorth, a lightweight online memory framework that learnsquery-dependent memory worthfromsparse execution feedbackand applies it consistently to memory retrieval andbounded memory management. Across threeLifelongAgentBenchenvironments and both local and API-based deployments,TokenWorthachieves the highest task success rate while using the fewest output tokens among the evaluated methods. These results suggest that effective lifelong adaptation under resource constraints depends not on remembering more, but on learning what is worth remembering. Our code is publicly available at https://github.com/AIGNLAI/TokenWorth.

View arXiv pageView PDFGitHub3Add to collection

Get this paper in your agent:

hf papers read 2610\.26453

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.26453 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.26453 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.26453 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.