Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.00756 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914620516597760 |
|---|---|
| author | Wang, Yannan Yang, Longli Liu, Zhen Kumar, Abhishek Maple, Carsten |
| author_facet | Wang, Yannan Yang, Longli Liu, Zhen Kumar, Abhishek Maple, Carsten |
| contents | Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection. Fine-tuning edge models after deployment is costly and difficult to scale across heterogeneous nodes, while purely local memory leaves agents with isolated experience and growing prompt context. We propose \textsc{CoMIC}, a parameter-update-free cloud-edge framework for Collaborative Memory and Insights Circulation. \textsc{CoMIC} follows a \textit{Centralized Reflection, Decentralized Execution} design: edge agents execute locally using subgoal-oriented hierarchical memory and selective re-expansion of relevant histories, while a cloud-side LLM critic asynchronously evaluates completed trajectories, filters reusable experience, and aggregates cross-agent guidance keyed by semantic subgoal identifiers. Across five long-horizon agent tasks spanning symbolic planning and text interaction, \textsc{CoMIC} improves progress rate and action grounding for weak edge agents and yields task-dependent success-rate gains without updating model parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00756 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems Wang, Yannan Yang, Longli Liu, Zhen Kumar, Abhishek Maple, Carsten Artificial Intelligence Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection. Fine-tuning edge models after deployment is costly and difficult to scale across heterogeneous nodes, while purely local memory leaves agents with isolated experience and growing prompt context. We propose \textsc{CoMIC}, a parameter-update-free cloud-edge framework for Collaborative Memory and Insights Circulation. \textsc{CoMIC} follows a \textit{Centralized Reflection, Decentralized Execution} design: edge agents execute locally using subgoal-oriented hierarchical memory and selective re-expansion of relevant histories, while a cloud-side LLM critic asynchronously evaluates completed trajectories, filters reusable experience, and aggregates cross-agent guidance keyed by semantic subgoal identifiers. Across five long-horizon agent tasks spanning symbolic planning and text interaction, \textsc{CoMIC} improves progress rate and action grounding for weak edge agents and yields task-dependent success-rate gains without updating model parameters. |
| title | CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2606.00756 |