PostTrainBench: Can LLM Agents Automate LLM Post-Training?
Tests whether agents can improve base models through post-training under a fixed compute budget.
Verify byline in the original ↗PUBLICATION BYLINE
Indexed publications with this author name. Affiliation and author identity require publication-specific evidence.
Tests whether agents can improve base models through post-training under a fixed compute budget.
Verify byline in the original ↗