Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Paper • 2605.09063 • Published 22 days ago • 80
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction Paper • 2605.05242 • Published 28 days ago • 116
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published 28 days ago • 166
view article Article DeepSeek-V4: a million-token context that agents can actually use burtenshaw • Apr 24 • 47
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published Apr 15 • 163
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance Paper • 2604.12627 • Published Apr 14 • 101