AI RESEARCH
Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards
arXiv CS.CL
•
ArXi:2510.04214v3 Announce Type: replace We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The agent must follow a multi-stage Standard Operating Procedure (SOP) and strict guardrails (no over-promising and no hallucinations), while remaining human-like and effective over long, multi-turn dialogues. We propose Reward-Enhanced Policy Optimization (REPO), a reinforcement learning post-