Search papers, labs, and topics across Lattice.
Arizona State University, Cisco Research
3
0
5
Critique-aware training can boost LLM agent reliability by over 10% in complex, stateful environments, transforming how we approach tool-calling tasks.
LedgerAgent's structured state management reduces policy violations and enhances decision-making accuracy in customer-service agents, outperforming traditional prompt-based methods.
Open-source LLM agents can get a 27% performance boost in tool use by strategically injecting context tailored to address their most common failure modes.
