MemoSync: Co-Managing Developer-Agent Metamemory Across Contexts

AI coding agents increasingly manage what context carries across sessions and projects, but developers have limited visibility into what these agents store, retrieve, and apply. This opacity creates a metamemory problem: the developer's meta-level judgments about what should be remembered are separated from the agent's object-level memory operations, disrupting the monitoring and control that keep the two levels aligned. We conducted a formative study with 12 developers and identified what they want to monitor and control across four dimensions of agent memory use. Based on these findings, we designed MemoSync, a co-management system that treats agent memory as a shared, operable representation: the agent proposes memory candidates and reports which items it uses, and the developer reviews, edits, and scopes them. In a between-subjects study (N=132) against two baselines, MemoSync participants achieved significantly higher task performance and the highest mean developer-agent memory alignment. In an exploratory mediation analysis, the alignment advantage was primarily driven by improved monitoring accuracy. Despite performing substantially more monitoring and control actions, participants reported no increase in perceived workload. A week-long deployment with nine developers showed that memory monitoring and control fit into everyday development work. MemoSync is open-sourced at https://github.com/SLEEPYBQ/MemoSync.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.24165
Primary Topic
Software Engineering Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

MemoSync: Co-Managing Developer-Agent Metamemory Across Contexts

Junze Li, Wenshuo Zhang, Dingdong Liu, Shiyuan Piao et al.
arXiv (Cornell University)
Software Engineering Research
preprint

MemoSync: Co-Managing Developer-Agent Metamemory Across Contexts

Junze Li, Wenshuo Zhang, Dingdong Liu, Shiyuan Piao, Xiaojuan Ma, Baiqiao Zhang, Shuai Ma, Yuying Tang, Chunyang Luo
preprint en

Abstract

AI coding agents increasingly manage what context carries across sessions and projects, but developers have limited visibility into what these agents store, retrieve, and apply. This opacity creates a metamemory problem: the developer's meta-level judgments about what should be remembered are separated from the agent's object-level memory operations, disrupting the monitoring and control that keep the two levels aligned. We conducted a formative study with 12 developers and identified what they want to monitor and control across four dimensions of agent memory use. Based on these findings, we designed MemoSync, a co-management system that treats agent memory as a shared, operable representation: the agent proposes memory candidates and reports which items it uses, and the developer reviews, edits, and scopes them. In a between-subjects study (N=132) against two baselines, MemoSync participants achieved significantly higher task performance and the highest mean developer-agent memory alignment. In an exploratory mediation analysis, the alignment advantage was primarily driven by improved monitoring accuracy. Despite performing substantially more monitoring and control actions, participants reported no increase in perceived workload. A week-long deployment with nine developers showed that memory monitoring and control fit into everyday development work. MemoSync is open-sourced at https://github.com/SLEEPYBQ/MemoSync.

arXiv (Cornell University)
Software Engineering Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon