Search papers, labs, and topics across Lattice.
3
0
6
Genuine agency in AI requires internalized structures, not just engineered workflows, to ensure true autonomy and safety.
LLM-based multi-agent systems are surprisingly vulnerable: a new RL-based attacker can evolve sophisticated, long-horizon attacks by exploiting trust in external tools.
Achieve SOTA reasoning performance with a 30B parameter model using up to 95% fewer tokens by explicitly controlling when and how deeply an LLM plans.
