# EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation

arXiv: https://arxiv.org/abs/2509.04310 · HTML: https://mlsanity.com/paper/2509.04310/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 6 of 6)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://mlsanity.com/paper/2406.14228/) (2024)
- [Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions](https://mlsanity.com/paper/2312.02913/) (2023)
- [ACE: A LLM-based Negotiation Coaching System](https://mlsanity.com/paper/2410.01555/) (2024)
- [Large Language Model Sentinel: LLM Agent for Adversarial Purification](https://mlsanity.com/paper/2405.20770/) (2024)

## Built on by (most cited first, 8 of 8)

- [EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration](https://mlsanity.com/paper/2604.07003/) (2026)
- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)
- [EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation](https://mlsanity.com/paper/2511.03370/) (2025)
- [MERIT Feedback Elicits Better Bargaining in LLM Negotiators](https://mlsanity.com/paper/2602.10467/) (2026)
- [How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study](https://mlsanity.com/paper/2604.00005/) (2026)
- [EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation](https://mlsanity.com/paper/2605.26785/) (2026)
- [From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue](https://mlsanity.com/paper/2607.07824/) (2026)
- [How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation](https://mlsanity.com/paper/2607.25140/) (2026)

## Abstract (arXiv)

Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in textitcomplex, textitmulti-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 hrefhttps://github.com/Yunbo-max/EvoEmotextcolorredhttps://github.com/Yunbo-max/EvoEmo.