ADSKAILab/Zero-To-CAD-1m
Viewer • Updated • 1,000k • 6.98k • 46
Raymond Weitekamp
rawwerks
AI & ML interests
None yet
Recent Activity
liked a dataset about 6 hours ago
ADSKAILab/Zero-To-CAD-1m liked a model 19 days ago
Qwen/Qwen3.6-35B-A3B liked a model 22 days ago
mit-oasys/rlm-qwen3-8b-v0.1Organizations
liked a
dataset about 6 hours ago
liked a
model 19 days ago
liked a
model 22 days ago
liked a
model 25 days ago
liked a
model about 1 month ago
liked 2
models about 2 months ago
liked a
dataset about 2 months ago
upvoted a collection 3 months ago
liked 5
models 3 months ago
mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 1.16M • 840
TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF
30B • Updated • 13.1k • 505
inference-net/Schematron-3B
Text Generation • 3B • Updated • 2.59k • • 332
Banafo/Kroko-ASR
Automatic Speech Recognition • Updated • 81
ByteDance-Seed/Stable-DiffCoder-8B-Instruct
Text Generation • 8B • Updated • 2.07k • 136
liked 5
models 4 months ago
z-lab/Qwen3-Coder-30B-A3B-DFlash
Text Generation • 0.5B • Updated • 1.84k • 29
cerebras/GLM-4.7-REAP-218B-A32B
Text Generation • 218B • Updated • 75 • 32
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 95.5k • 216
zai-org/GLM-4.7
Text Generation • 358B • Updated • 92.1k • • 2.03k
LiquidAI/LFM2-2.6B-Exp
Text Generation • 3B • Updated • 6.49k • 339
reacted to Kseniase's post with ❤️ 5 months ago
Post
6354
9 Recent advances in Multi-Agent Systems (all open-source)
The idea to split tasks across multiple agents instead of relying on one universal agent is now seen as one of the most effective ways to build an AI stack. Concepts like “agent swarms” were highlighted at the AI Engineer Code Summit in NYC (Nov 20–21) as the winning architecture. And this trend is not only about coding and software. It applies across all AI domains.
So here is some recent research that helps keep multi-agent systems (MAS) better and up-to-date:
1. LatentMAS → Latent Collaboration in Multi-Agent Systems (2511.20639)
AI agents share their hidden "thoughts" directly in latent space instead of talking through text. This makes collaboration and reasoning way faster and accurate (no extra training needed)
2. Puppeteer → Multi-Agent Collaboration via Evolving Orchestration (2505.19591)
Uses a “puppeteer” LLM that dynamically decides which agents (“puppets”) to call and in what order. By learning this orchestration with reinforcement learning (RL), the system solves complex tasks more efficiently and with fewer compute costs
3. MADD → MADD: Multi-Agent Drug Discovery Orchestra (2511.08217)
A MAS with 4 agents for drug discovery. It lets researchers describe a drug discovery task in plain language. Then MADD automatically builds and runs the full hit-identification pipeline, making AI-driven drug design a simple end-to-end workflow
4. Multi-Agent Tool-Integrated Policy Optimization (MATPO) → Multi-Agent Tool-Integrated Policy Optimization (2510.04678)
Lets one LLM act as multiple agents (like a planner and a worker) by using different prompts and training them together with RL. So you get the benefits of a multi-agent system without needing multiple models
If you're interested in trends in multi-agent for software development of the future, explore my article with the emergent playbook. This is super interesting → https://www.turingpost.com/p/aisoftwarestack
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
Read further below ⬇️
The idea to split tasks across multiple agents instead of relying on one universal agent is now seen as one of the most effective ways to build an AI stack. Concepts like “agent swarms” were highlighted at the AI Engineer Code Summit in NYC (Nov 20–21) as the winning architecture. And this trend is not only about coding and software. It applies across all AI domains.
So here is some recent research that helps keep multi-agent systems (MAS) better and up-to-date:
1. LatentMAS → Latent Collaboration in Multi-Agent Systems (2511.20639)
AI agents share their hidden "thoughts" directly in latent space instead of talking through text. This makes collaboration and reasoning way faster and accurate (no extra training needed)
2. Puppeteer → Multi-Agent Collaboration via Evolving Orchestration (2505.19591)
Uses a “puppeteer” LLM that dynamically decides which agents (“puppets”) to call and in what order. By learning this orchestration with reinforcement learning (RL), the system solves complex tasks more efficiently and with fewer compute costs
3. MADD → MADD: Multi-Agent Drug Discovery Orchestra (2511.08217)
A MAS with 4 agents for drug discovery. It lets researchers describe a drug discovery task in plain language. Then MADD automatically builds and runs the full hit-identification pipeline, making AI-driven drug design a simple end-to-end workflow
4. Multi-Agent Tool-Integrated Policy Optimization (MATPO) → Multi-Agent Tool-Integrated Policy Optimization (2510.04678)
Lets one LLM act as multiple agents (like a planner and a worker) by using different prompts and training them together with RL. So you get the benefits of a multi-agent system without needing multiple models
If you're interested in trends in multi-agent for software development of the future, explore my article with the emergent playbook. This is super interesting → https://www.turingpost.com/p/aisoftwarestack
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
Read further below ⬇️
- 2 replies