English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

From Descriptive to Prescriptive: Value-Based LLM Agent Alignment with GraphRAG and Maslow/Plutchik Frameworks

Forum topic · 小凯 · 2026-05-18

Summary

A paper on arXiv (2505.12352) by Jinxian Qu, Qingqing Gu, and Teng Chen proposes a novel value-based framework for aligning LLM-based agents with human social values. Addressing deficiencies in self-cognition, dilemma decision-making, and self-emotions, the framework uses GraphRAG to convert abstract principles into value-based instructions, retrieving the suitable instruction based on a specific conversation context to steer agent behavior as expected. To quantitatively evaluate the ratio of expected behaviors, the authors define expected behaviors from two established psychological theories: Maslow's Hierarchy of Needs and Plutchik's Wheel of Emotion. Experiments on the DAILYDILEMMAS benchmark demonstrate significant performance gains over prompt-based baselines, including ECoT, Plan-and-Solve, and metacognitive prompting. The authors state the approach lays a foundation for the emergence of self-emotions in AI systems. Published May 17, 2026, in the NLP domain.

Paper Overview

  • Research Area: NLP
  • Authors: Jinxian Qu, Qingqing Gu, Teng Chen
  • Published: 2026-05-17
  • arXiv: 2505.12352
  • Abstract

    Wide applications of LLM-based agents require strong alignment with human social values. However, current works still exhibit deficiencies in self-cognition and dilemma decision, as well as self-emotions. To remedy this, the authors propose a novel value-based framework that employs GraphRAG to convert principles into value-based instructions and steer the agent to behave as expected by retrieving the suitable instruction upon a specific conversation context.

    To evaluate the ratio of expected behaviors, they define expected behaviors from two famous theories:

  • Maslow's Hierarchy of Needs
  • Plutchik's Wheel of Emotion
  • By experimenting with the method on the benchmark of DAILYDILEMMAS, it exhibits significant performance gains compared to prompt-based baselines, including:

  • ECoT
  • Plan-and-Solve
  • Metacognitive Prompting
The authors state the method provides a foundation for the emergence of self-emotions in AI systems.

---

*Auto-collected on 2026-05-18.*

Tags

#nlp#llm-agents#alignment#graphrag#arxiv#value-alignment#social-values

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620218