Glad to share our recent work on graph reasoning of LLMs.

🙅 We don’t need LLMs as solvers of graph problems like shortest path. (already have Dijkstra) 🤔 What we need: learn from synthetic graphs and generalize to real-world problems with graph implications. (e.g. multi-hop QA) 💡 We unlock this generalization with alignment and RL.

Introducing the Model Collaboration Tour 🤖🤝 Compositional intelligence. Collaborative development. Decentralized AI. By the Many. The methods. The vision. The hot takes. The comedy. LA folks, join us this week! Get your tickets by asking me to give a talk @ your lab/school!

now accepted at ICLR 26 full implementation of this (and many other methods 😉) coming soon