Search papers, labs, and topics across Lattice.
Beihang University
3
0
4
Self-conditioning on verified trajectories boosts reinforcement learning performance by over 8%, revealing the power of internal feedback in credit assignment.
LLM agents can get 18% better at tasks by co-evolving their skills and tools, instead of learning them separately.
Current AI memory systems are surprisingly bad at integrating diverse, real-world information across long time spans, as evidenced by a new benchmark where they only achieve 55% accuracy.
