Decentralized Multi-Agent Systems with Shared Context
Multi-agent systems (MAS) can scale large language model agents on long-horizon tasks by running them in parallel, yet existing designs waste much of this parallelism in bubbles: agent time spent waiting on others or redoing a peer's work. These bubbles stem from how agents communicate. Independent agents share nothing and rediscover what their peers have already found; peer-communicating agents wait at synchronous rounds; and under centralized orchestration, the main agent blocks on its sub-agents while progress is relayed. We propose Decentralized Language Models (DeLM), a MAS framework on top of existing agent harnesses that squeezes out these bubbles by replacing the main agent with a...
| Authors | Yuzhen Mao, Jerry Gu, Aadi Chauhan et al. |
|---|---|
| Primary category | cs.MA |
| Published | 9 June 2026 |
| Last updated at source | 4 October 2026 |
Connected in the knowledge graph
- yuzhenm/delm-720-trajectoriesDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.