Search papers, labs, and topics across Lattice.
3
1
5
7
Self-evolving LLM agents show variable reliability in dynamic task environments, challenging the notion that stronger models always yield better adaptation.
Generative retrieval can achieve both shared modeling and objective-specific control, leading to significant improvements in user engagement metrics.
Test-time RL's vulnerability to noisy pseudo-labels is amplified by group-relative advantage estimation, but can be mitigated with a surprisingly simple debiasing and denoising approach.
