{"id":5079,"date":"2025-09-08T15:13:35","date_gmt":"2025-09-08T07:13:35","guid":{"rendered":"https:\/\/www.rzautoassembly.com\/?p=5079"},"modified":"2025-09-08T15:13:35","modified_gmt":"2025-09-08T07:13:35","slug":"artificial-intelligence-is-about-to-undergo-its-biggest-upgrade-to-date-emotional-intelligence","status":"publish","type":"post","link":"https:\/\/www.rzautoassembly.com\/ko\/artificial-intelligence-is-about-to-undergo-its-biggest-upgrade-to-date-emotional-intelligence\/","title":{"rendered":"Artificial intelligence is about to undergo its biggest upgrade to date: emotional intelligence."},"content":{"rendered":"

 <\/p>\n

\"\"<\/a>
\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0emotional intelligence<\/figcaption><\/figure>\n

Endowing Artificial Intelligence with Personality<\/span><\/strong><\/p>\n

 <\/p>\n

In the book \u201cPsychologically Augmented AI Agents\u201d, Maciej Besta from ETH Zurich in Switzerland and his colleagues propose a framework called \u201cMBTI-in-Thoughts\u201d. Instead of retraining the model, they rely on prompt engineering to lock in personality traits along cognitive and emotional axes.<\/p>\n

 <\/p>\n

The authors write, \u201cOur approach draws on the Myers-Briggs Type Indicator (MBTI) to inject different personality archetypes into agents through prompt engineering.\u201d They add that this makes it possible to \u201ccontrol behavior along two fundamental dimensions of human psychology: cognition and emotion\u201d.<\/p>\n

 <\/p>\n

The researchers verified this by endowing language models with traits such as \u201cemotionally expressive\u201d or \u201canalytical\u201d, and then measuring their performance. Expressive agents excelled at narrative generation; analytical agents were better at game-theoretic reasoning. To ensure these personality traits could be effectively applied, the team used the \u201c16Personalities\u201d test for validation.<\/p>\n

 <\/p>\n

\u201cTo ensure the persistence of traits, we integrated the official 16Personalities test for automatic verification,\u201d the paper explains. In other words: AI must consistently pass human personality tests to be deemed psychologically ready.<\/p>\n

 <\/p>\n

The end result is that developers can summon agents with consistent roles (a compassionate assistant, a calm and rational negotiator, a dramatic storyteller) without modifying the underlying model.<\/p>\n

 <\/p>\n

Teaching AI to Feel in Real Time<\/span><\/strong><\/p>\n

 <\/p>\n

Meanwhile, \u201cEvoEmo: Evolutionary Emotional Policies for LLM Agents in Multi-turn Negotiations\u201d, co-authored by Yun Bolong and the University of Cambridge, addresses the opposite issue: not just what kind of personality an agent has, but how it dynamically shifts emotions during a negotiation.<\/p>\n

 <\/p>\n

The system models emotions as part of a Markov decision process, a mathematical framework where outcomes depend not only on current choices but also on a sequence of previous states and probabilistic transitions. EvoEmo then uses evolutionary reinforcement learning to optimize these emotional paths. As the authors state:<\/p>\n

 <\/p>\n

\u201cEvoEmo models emotional state transitions as a Markov decision process and employs population-based genetic optimization to develop high-reward emotional strategies across different negotiation scenarios.\u201d<\/p>\n

 <\/p>\n

Instead of fixing an agent\u2019s emotional tone, EvoEmo allows the model to adjust according to the course of the conversation\u2014becoming \uff0cconfident, or skeptical. In tests, EvoEmo agents consistently outperformed both ordinary baseline agents and static emotional agents.<\/p>\n

 <\/p>\n

The paper notes, \u201cEvoEmo consistently outperformed both benchmarks, achieving higher success rates, greater efficiency, and more cost savings for buyers.\u201d<\/p>\n

 <\/p>\n

In short: emotional intelligence is not just superficial. It can significantly improve outcomes in tasks such as negotiations.<\/p>\n

\"\"<\/a>
\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 emotional intelligence<\/figcaption><\/figure>\n

Two Sides of the Same Coin<\/span><\/strong><\/p>\n

 <\/p>\n

At first glance, these two papers seem unrelated. One is about archetypes, the other about strategies. But read together, they paint a two-part blueprint for the future evolution of AI:<\/p>\n

 <\/p>\n

MBTI-in-Thoughts ensures that agents have consistent personalities\u2014empathetic or rational, expressive or reserved. EvoEmo ensures that agents\u2019 personalities can flex during conversations and shape outcomes through emotional strategies. It is crucial to have both.<\/p>\n

 <\/p>\n

For example, imagine a customer service robot that is as patient and enthusiastic as an advisor but knows when to stand firm on its policies; or a negotiation robot that starts off conciliatory but becomes tougher as risks increase. Even a\u00a0sheet automatic loading robot<\/span><\/b><\/u><\/strong><\/a>\u00a0<\/span>in an industrial setting can be endowed with the fixed trait of \u201cprecision and meticulousness\u201d under the MBTI framework to ensure accurate sheet gripping, while using EvoEmo\u2019s dynamic strategies to adjust the strength and response speed according to changes in sheet thickness and conveying rhythm, reducing losses while ensuring feeding efficiency\u2014this is a vivid example of how emotional intelligence enhances task performance in non-interactive scenarios.<\/p>\n

 <\/p>\n

The story of AI evolution has largely revolved around scale\u2014more parameters, more data, stronger reasoning ability. These two papers suggest that an emerging chapter may be related to the emotional dimension: endowing agents with a personality skeleton and teaching them to manipulate these \u201cmuscles\u201d in real time. The next generation of chatbots will not only think harder; they will also sulk, flatter, and calculate more intentionally.<\/p>\n

 <\/p>\n

What is the market size and development trend of medical product assembly machines?<\/a><\/span><\/p>\n

What are the advantages of medical product assembly machines?<\/a><\/span><\/p>","protected":false},"excerpt":{"rendered":"

  Endowing Artificial Intelligence with Personality \u00a0 In the book \u201cPsychologically Augmented AI Agents\u201d, Maciej Besta from ETH Zurich in Switzerland and his colleagues propose a framework called \u201cMBTI-in-Thoughts\u201d. Instead of retraining the model, they rely on prompt engineering to lock in personality traits along cognitive and emotional axes. \u00a0 The authors write, \u201cOur approach [\u2026]<\/p>","protected":false},"author":1,"featured_media":5081,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1,124],"tags":[],"class_list":["post-5079","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","category-technology"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/posts\/5079","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/comments?post=5079"}],"version-history":[{"count":0,"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/posts\/5079\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/media\/5081"}],"wp:attachment":[{"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/media?parent=5079"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/categories?post=5079"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rzautoassembly.com\/ko\/wp-json\/wp\/v2\/tags?post=5079"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}