3 papers
cs.LG2026
Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
George Yakushev, Nataliia Babina, Masoud Vahid Dastgerdi +4
Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also makes them less interactive: give…
cs.CL2026
Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs
Panatchakorn Anantaprayoon, Nataliia Babina, Nima Asgharbeygi +1
LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI f…
cs.CL2025
Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment
Panatchakorn Anantaprayoon, Nataliia Babina, Jad Tarifi +1
Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI s…