2 papers
cs.CL2026
Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations
Lior Baruch, Moshe Butman, Kfir Bar +1
Developing dialogue systems capable of engaging in multi-turn, goal-oriented conversations remains a significant challenge, especially in specialized domains with limited data. Thi…
cs.MA2026
Why Study Emergent Behavior When You Can Regulate It? Aligning Multi-Agent Systems with Reward Prediction
Assaf Caftory, Almog Zemach, Moshe Butman +1
Multi-agent simulations are widely used to study complex social and ecological systems, where rich and often unexpected emergent behaviors arise from local interactions. A large bo…