EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation
This work addresses the need for more effective and adaptive LLM agents in adversarial negotiation scenarios, representing an incremental improvement by focusing on emotional strategies.
The paper tackles the problem of LLM agents being vulnerable in multi-turn price negotiations due to passive emotional responses by introducing EvoEmo, an evolutionary reinforcement learning framework that optimizes dynamic emotional expression, resulting in higher success rates, efficiency, and buyer savings compared to baselines.
Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, existing LLM agents largely overlook the functional role of emotions in such negotiations, instead generating passive, preference-driven emotional responses that make them vulnerable to manipulation and strategic exploitation by adversarial counterparts. To address this gap, we present EvoEmo, an evolutionary reinforcement learning framework that optimizes dynamic emotional expression in negotiations. EvoEmo models emotional state transitions as a Markov Decision Process and employs population-based genetic optimization to evolve high-reward emotion policies across diverse negotiation scenarios. We further propose an evaluation framework with two baselines -- vanilla strategies and fixed-emotion strategies -- for benchmarking emotion-aware negotiation. Extensive experiments and ablation studies show that EvoEmo consistently outperforms both baselines, achieving higher success rates, higher efficiency, and increased buyer savings. This findings highlight the importance of adaptive emotional expression in enabling more effective LLM agents for multi-turn negotiation.