Excited to share that "Grounded Test-Time Adaptation for LLM Agents" (GTTA) has been accepted to #ICLR2026! 馃帀
LLM agents often fail in novel environments. We enable them to adapt at test time via self-initiated exploration -- no fine-tuning required. 馃殌
- 馃敟The quality of synthetic data matters more than its size. We introduce SynQuE - a framework that ranks synthetic datasets by their real-world usefulness without any labeled real data (e.g., benchmarks). Select better training synthetic data, train better models.

