EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration

• URL: http://arxiv.org/abs/2604.07003v2
• Date: Sun, 12 Apr 2026 13:22:43 GMT
• Title: EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration
• Abstract summary: Large language models (LLMs) has been widely used for automated negotiation, but their high computational cost and privacy risks limit deployment in privacy-sensitive, on-device settings such as mobile assistants or rescue robots.<n>We introduce EmoMAS, a Bayesian multi-agent framework that transforms emotional decision-making from reactive to strategic.
• Score: 26.485737549410405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) has been widely used for automated negotiation, but their high computational cost and privacy risks limit deployment in privacy-sensitive, on-device settings such as mobile assistants or rescue robots. Small language models (SLMs) offer a viable alternative, yet struggle with the complex emotional dynamics of high-stakes negotiation. We introduces EmoMAS, a Bayesian multi-agent framework that transforms emotional decision-making from reactive to strategic. EmoMAS leverages a Bayesian orchestrator to coordinate three specialized agents: game-theoretic, reinforcement learning, and psychological coherence models. The system fuses their real-time insights to optimize emotional state transitions while continuously updating agent reliability based on negotiation feedback. This mixture-of-agents architecture enables online strategy learning without pre-training. We further introduce four high-stakes, edge-deployable negotiation benchmarks across debt, healthcare, emergency response, and educational domains. Through extensive agent-to-agent simulations across all benchmarks, both SLMs and LLMs equipped with EmoMAS consistently surpass all baseline models in negotiation performance while balancing ethical behavior. These results show that strategic emotional intelligence is also the key driver of negotiation success. By treating emotional expression as a strategic variable within a Bayesian multi-agent optimization framework, EmoMAS establishes a new paradigm for effective, private, and adaptive negotiation AI suitable for high-stakes edge deployment.

Related papers

• EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization [14.12747683387614]
  We propose a novel Reinforcement Learning-based Dynamic Agent framework (textbfEmoAgent-R1) to optimize the emotion recognition, reasoning, and abilities of an MLLM with dynamic agent specialization based on reinforcement learning.<n>Experiments on multimodal emotion recognition benchmarks demonstrate the superiority of our EmoAgent-R1 in stronger emotion reasoning performance and improved optimization stability.
  arXiv  Detail & Related papers  (2026-07-23T07:52:40Z)
• EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation [44.481959726034574]
  We introduce textbfEmoDistill, an offline framework for distilling emotional negotiation skills into language model agents.<n>EmoDistill decomposes emotional strategy into emotion selection and emotion expression.<n>Across four emotion-sensitive negotiation domains, SLM policies trained under the EmoDistill framework achieve the highest utility.
  arXiv  Detail & Related papers  (2026-05-26T09:54:53Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation [66.09161596959771]
  Small language models (SLMs) offer a practical alternative, but suffer from a significant performance gap compared to large language models (LLMs)<n>This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas.<n>We show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size.
  arXiv  Detail & Related papers  (2025-11-05T11:25:07Z)
• Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading [57.28635022507172]
  TiMi is a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment.<n>We propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection.
  arXiv  Detail & Related papers  (2025-10-06T13:08:55Z)
• EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation [61.627248012799704]
  Existing Large Language Models (LLMs) agents largely overlook the functional role of emotions in such negotiations.<n>We present EvoEmo, an evolutionary reinforcement learning framework that optimize dynamic emotional expression in negotiations.
  arXiv  Detail & Related papers  (2025-09-04T15:23:58Z)
• EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery [65.30120701878582]
  Large Language Model (LLM) agents are vulnerable to exploitation in emotion-sensitive domains like debt collection.<n>EmoDebt is an emotional intelligence engine that reframes a model's ability to express emotion in negotiation as a sequential decision-making problem.<n>EmoDebt achieves significant strategic robustness, substantially outperforming non-adaptive and emotion-agnostic baselines.
  arXiv  Detail & Related papers  (2025-03-27T01:41:34Z)
• Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation [52.930183136111864]
  We propose using scorable negotiation to evaluate Large Language Models (LLMs) To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark.
  arXiv  Detail & Related papers  (2023-09-29T13:33:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.