Search papers, labs, and topics across Lattice.
8
8
15
3
This work proposes a generational genetic algorithm to coordinate specialized large language model agents that integrate mechanistic arguments, reconsider assumptions, and assess evidence and testability that advances a vision of autonomous science in which AI research teams achieve a capacity for discovery beyond that of individual models.
The Mind2Dialogue framework proposes a psychology-guided simulator that preserves personal characteristics while updating mental states through interaction to generate coherent conversations, and trains models on the Oracle's well-informed responses to assist users without direct access to their mental states at deployment.
Today's best AI agents still fail more than half the time on real-world tasks combining vision, search, and coding, revealing critical gaps in reasoning and tool use.
Forget simple scaling laws: the compute-optimal number of parallel rollouts in LLM RL plateaus, revealing distinct mechanisms for easy vs. hard problems.
User behavior, not just hardware, may be the biggest lever for reducing device power consumption.
Key contribution not extracted.
Forget rigid game environments – PAN lets you simulate open-world scenarios with language-specified actions and long-term visual coherence, opening the door to more realistic AI training.
