Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
8
Frontier models can be used sparingly for long-horizon tasks by a weak agent that learns to predict when it needs help, then keeps the strong model on a leash.
Fine-grained credit assignment in LLM agents can be unreliable due to downstream randomness, but AdaStep's optimal shrinkage coefficient precisely balances local and global rewards.
LLM agents struggle with exploration in multi-agent settings, leading to poor coordination and increased regret, but a new framework can turn this around.