2606.10532v1 Jun 09, 2026 cs.AI

ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning

Huawei Shen
Huawei Shen
Citations: 51
h-index: 4
Liang Pang
Liang Pang
Citations: 784
h-index: 16
Wenbin Duan
Wenbin Duan
Citations: 12
h-index: 2
Yunhan Jiang
Yunhan Jiang
Citations: 10
h-index: 2
Xiaoqian Sun
Xiaoqian Sun
Citations: 13
h-index: 1
Shasha Guo
Shasha Guo
Citations: 232
h-index: 7

Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks. Existing memory mechanisms are largely centralized, typically organizing retrieved information and interaction history within a single model context. This design imposes a fundamental trade-off: scaling reasoning trajectories risks context overload, whereas aggressive content pruning may result in irreversible information loss. Seeking a better trade-off, we draw inspiration from human cognitive systems, especially the functional complementarity between the prefrontal cortex (executive control) and the hippocampus (memory management), suggesting that such a trade-off need not be inherent, but may instead stem from centralized memory organization. To this end, we propose ActiveMem, a heterogeneous framework that decouples agent memory from the core reasoning process. Specifically, a high-level Planner utilizes distilled semantic gists to execute reasoning, while a lightweight, distributed memory system operates in parallel to actively accumulate and consolidate these gists throughout the task. Experiments on BrowseComp-Plus and GAIA show that ActiveMem achieves state-of-the-art accuracy with significantly reduced overhead, demonstrating the effectiveness of distributed active memory for long-horizon reasoning.

0 Citations
0 Influential
8 Altmetric
40.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!