Paper
Collaborative Multi-Agent Optimization for Personalized Memory System
Authors
Wenyu Mao, Haoyang Liu, Zhao Liu, Haosong Tan, Yaorui Shi, Jiancan Wu, An Zhang, Xiang Wang
Abstract
Memory systems are crucial to personalized LLMs by mitigating the context window limitation in capturing long-term user-LLM conversations. Typically, such systems leverage multiple agents to handle multi-granular memory construction and personalized memory retrieval tasks. To optimize the system, existing methods focus on specializing agents on their local tasks independently via prompt engineering or fine-tuning. However, they overlook cross-agent collaboration, where independent optimization on local agents hardly guarantees the global system performance. To address this issue, we propose a Collaborative Reinforcement Learning Framework for Multi-Agent Memory Systems (CoMAM), jointly optimizing local agents to facilitate collaboration. Specifically, we regularize agents' execution as a sequential Markov decision process (MDP) to embed inter-agent dependencies into the state transition, yielding both local task rewards (e.g., information coverage for memory construction) and global rewards (i.e., query-answer accuracy). Then, we quantify each agent's contribution via group-level ranking consistency between local and global rewards, treating them as adaptive weights to assign global credit and integrate local-global rewards. Each agent is optimized by these integrated rewards, aligning local improvements with the global performance. Experiments show CoMAM outperforms leading memory systems, validating the efficacy of our proposed collaborative reinforcement learning for joint optimization.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.12631v1</id>\n <title>Collaborative Multi-Agent Optimization for Personalized Memory System</title>\n <updated>2026-03-13T04:04:17Z</updated>\n <link href='https://arxiv.org/abs/2603.12631v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.12631v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Memory systems are crucial to personalized LLMs by mitigating the context window limitation in capturing long-term user-LLM conversations. Typically, such systems leverage multiple agents to handle multi-granular memory construction and personalized memory retrieval tasks. To optimize the system, existing methods focus on specializing agents on their local tasks independently via prompt engineering or fine-tuning. However, they overlook cross-agent collaboration, where independent optimization on local agents hardly guarantees the global system performance. To address this issue, we propose a Collaborative Reinforcement Learning Framework for Multi-Agent Memory Systems (CoMAM), jointly optimizing local agents to facilitate collaboration. Specifically, we regularize agents' execution as a sequential Markov decision process (MDP) to embed inter-agent dependencies into the state transition, yielding both local task rewards (e.g., information coverage for memory construction) and global rewards (i.e., query-answer accuracy). Then, we quantify each agent's contribution via group-level ranking consistency between local and global rewards, treating them as adaptive weights to assign global credit and integrate local-global rewards. Each agent is optimized by these integrated rewards, aligning local improvements with the global performance. Experiments show CoMAM outperforms leading memory systems, validating the efficacy of our proposed collaborative reinforcement learning for joint optimization.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n <published>2026-03-13T04:04:17Z</published>\n <arxiv:primary_category term='cs.MA'/>\n <author>\n <name>Wenyu Mao</name>\n </author>\n <author>\n <name>Haoyang Liu</name>\n </author>\n <author>\n <name>Zhao Liu</name>\n </author>\n <author>\n <name>Haosong Tan</name>\n </author>\n <author>\n <name>Yaorui Shi</name>\n </author>\n <author>\n <name>Jiancan Wu</name>\n </author>\n <author>\n <name>An Zhang</name>\n </author>\n <author>\n <name>Xiang Wang</name>\n </author>\n </entry>"
}