It was brought to my attention that Decentralized Multi-Agent Systems with Shared Context (DeLM) has a project website that also lists those findings and graphs: https://yuzhenmao.github.io/DeLM/
agent-swarm.dev is open source/MIT exactly meant for these scenarios.
Particularly interesting for you, our lasts posts on how we handle to have efficient dreaming focused on reducing costs.
tl;dr: there's a self-driven process generating more effective and efficient prompts, code, and potentially select systemone models to tackle the cost problems.
We have companies using the system that we understand have stayed 'flat' in token consumption but with increasing workloads (ie. more workflows running).
Links from the post:
[1] Stanford CS146S: How always-on agents work
Lecture: https://www.youtube.com/watch?v=L1OBRtfPS34
Slides: https://drive.google.com/file/d/1b8WiBk_lcB3ue-jZMLijSUMLj6S...
[2] CMU 11-768 AI Agents: https://www.cmu-agents.com/#/schedule
[3] Decentralized Multi-Agent Systems with Shared Context (figure 3, page 3): https://arxiv.org/pdf/2606.10662
It was brought to my attention that Decentralized Multi-Agent Systems with Shared Context (DeLM) has a project website that also lists those findings and graphs: https://yuzhenmao.github.io/DeLM/
agent-swarm.dev is open source/MIT exactly meant for these scenarios.
Particularly interesting for you, our lasts posts on how we handle to have efficient dreaming focused on reducing costs.
tl;dr: there's a self-driven process generating more effective and efficient prompts, code, and potentially select systemone models to tackle the cost problems.
We have companies using the system that we understand have stayed 'flat' in token consumption but with increasing workloads (ie. more workflows running).
Hope it helps!
[flagged]
[flagged]
[flagged]