Abstract: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. The code is available at \href{this https URL}{\textcolor{red}{this https URL}}.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2509.04310 [cs.AI] |
| (or arXiv:2509.04310v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2509.04310 arXiv-issued DOI via DataCite |
From: Yunbo Long [view email]
[v1]
Thu, 4 Sep 2025 15:23:58 UTC (3,028 KB)
[v2]
Tue, 9 Sep 2025 02:43:02 UTC (3,028 KB)
[v3]
Mon, 13 Oct 2025 16:04:56 UTC (16,603 KB)
[v4]
Tue, 26 May 2026 11:47:58 UTC (16,598 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。