TTCS: Test-Time Curriculum Synthesis for Self-Evolving Paper • 2601.22628 • Published 24 days ago • 35
BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search Paper • 2601.11037 • Published Jan 16 • 18
FaithEval Benchmark Collection A collection of contextual QA datasets dedicated to evaluate the contextual faithfulness of LLMs • 3 items • Updated Oct 31, 2025 • 3