Search papers, labs, and topics across Lattice.
Rutgers University
4
0
7
7
ChronoMem allows LLM agents to seamlessly roll back their memory states, dramatically enhancing their ability to handle corrections and evolving information.
Local Branch Routing enables language models to leverage contextual evidence for decision-making without the computational burden of full solution searches, leading to substantial improvements in reasoning accuracy.
Forget complex architectures: the secret to self-improving LLM agents lies in teaching them how to *interpret* their past failures, not just remember them.
Stop benchmarking agent components in isolation; AgentSelect lets you train models to recommend *entire* agent configurations based on narrative queries.
