RewardHarness: Self-Evolving Agentic Post-Training
Paper • 2605.08703 • Published • 245
Joan Fuentes
joafuentes
AI & ML interests
Open-source multimodal experiment workflows. Sharing reproducible results.
Recent Activity
upvoted a paper 2 days ago
RewardHarness: Self-Evolving Agentic Post-Training upvoted a paper 2 days ago
Aspire: Can Models Self-Evolve from Vague Goals? upvoted a paper 5 days ago
Post-Training Leaves Behavioral Shadows on Unrelated DecisionsOrganizations
None yet