ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems
- Published
- Source
- arXiv
- Paper number
- 376
- Field
- AI / General
- arXiv ID
- 2606.08702
Key points
- It distills past trajectories into typed signed memory cards to create reusable strategic units.
- It organizes the cards as typed graphs with supports, satisfies, conflicts, and constrains relations.
- It uses needs-aware retrieval to search for cards that match the current task.
- It resolves conflicts and recovers dependencies through the relation graph to produce consistent guidance.
- Context-budget control prunes more than 50% of candidate cards and reduces planning overhead by 80%.
- It is training-free and does not require changes to the host model weights or orchestration.
Paper links
External research summaries. These are not HDATF publications or measured product results.