OProver: A Unified Framework for Agentic Formal Theorem Proving Paper • 2605.17283 • Published 4 days ago • 29
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? Paper • 2605.06527 • Published 14 days ago • 42
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context Paper • 2605.13831 • Published 8 days ago • 85
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining Paper • 2603.11103 • Published Mar 11 • 9
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining Paper • 2603.11103 • Published Mar 11 • 9
Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems Paper • 2509.22845 • Published Sep 26, 2025
OpenResearcher Collection OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis • 8 items • Updated Mar 24 • 18