Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists Paper • 2607.11079 • Published 4 days ago • 4
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering Paper • 2603.28583 • Published 3 days ago • 7
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers Paper • 2607.00394 • Published 16 days ago • 6
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory Paper • 2605.01688 • Published May 3 • 2
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? Paper • 2605.06527 • Published May 7 • 47
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context Paper • 2605.13831 • Published May 13 • 90