Pinned Loading

1. ReportBench ReportBench Public

   A comprehensive benchmark for evaluating deep research agents on academic survey tasks

   Python 48 4

2. LLM-I LLM-I Public

   🚀 LLM-I: Transform LLMs into natural interleaved multimodal creators! ✨ Tool-use framework supporting image search, generation, code execution & editing

   Python 37 1

3. SamplingEvolve SamplingEvolve Public

   An experience-guided framework for evolving model trajectories at test time.

   Python 14 1