MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training

Excerpt

arXiv:2610.05398v1 Announce Type: new Abstract: Autonomous research seeks sustained model improvements through iterative experimentation and feedback. LLM agents show promise in automating machine learning and language-model post-training, but their ability to sustain multimodal improvement remains unclear. We introduce MMPostTrainBench, a benchmark spanning eight tasks in image, audio, video, and joint audio-video understanding and image-grounded software repair. Agents operate from a common ba