cs.AINov 11, 2026

MemCredit: From Relevance to Utility for Decision-Time Memory in Long-Horizon Web Agents

Authors: Quanjiang Guo, Sijie Wang, Qianyang Zhu, Ben Zhang, Jinchuan Zhang, Ke Yan, Zhao Kang

Organizations: UESTC China · Nanyang Technological University Singapore

Abstract

Large language model (LLM) agents increasingly operate over long Web interaction histories, making memory management critical for reliable and efficient decision making. Existing methods primarily optimize storage, retrieval, or compression, but the memories most semantically relevant to the current state are not necessarily those that most improve the agent's action. We introduce MemCredit, a decision-centric memory framework that shifts memory selection from semantic relevance to decision utility. MemCredit estimates the state-, reference-context-, and policy-conditional marginal contribution of individual memories through controlled counterfactual interventions, and distills these intervention-derived credits into a lightweight utility estimator. At inference time, semantic relevance is used only for high-recall candidate generation, while predicted utility arbitrates which memories are retained under a fixed token budget, without modifying the underlying agent policy or requiring additional environment interaction. We evaluate MemCredit on ALFWorld and WebShop against representative memory baselines. On ALFWorld, MemCredit achieves 86.57 SR@50 under a 500-token historical-memory budget, compared with 65.67% for BM25 retrieval. Counterfactual analysis further shows that memory utility is sparse, strongly state dependent, and poorly captured by semantic relevance. These results suggest that decision utility provides a more effective principle than relevance alone for long-horizon agent memory management.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents

    Aug 3, 2026Jiajun Dong, Yutao Hu, Fengrui Fan +3LLM Agent MemoryLong-Horizon LLM Agents

  2. Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents

    Aug 21, 2026Quang Dao, Purvi Kathalkar, Kenneth EatonLLM Agent MemoryMemory Management for LLM Agents