PulseAugur
EN
LIVE 07:31:01

New Benchmark Assesses LLM Agents' Human-like Psychology

By PulseAugur Editorial · [2 sources] ·

Researchers have developed HEART-Bench, a new benchmark designed to evaluate whether large language model (LLM) agents can exhibit human-like psychology. The benchmark constructs 11 distinct characters based on the Big Five personality traits, each with 1,000 autobiographical memories. These agents are then subjected to 64 decision-making scenarios derived from the DIAMONDS taxonomy to assess their ability to make behaviorally consistent choices. AI

IMPACT This benchmark could lead to more sophisticated LLM agents capable of nuanced emotional and psychological responses.

RANK_REASON The cluster contains a research paper introducing a new benchmark for evaluating LLM agents.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New Benchmark Assesses LLM Agents' Human-like Psychology

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Weihan Peng, Chenxu Zhang, Qianao Wang, Yuling Shi, Heng Lian, Qihong Mao, Jiahao Pang, Chunliang Feng, Bowen Li, Xiaodong Gu ·

    HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?

    arXiv:2605.30058v1 Announce Type: new Abstract: While LLM agents have demonstrated remarkable task-oriented abilities such as planning, reasoning, and action, few works have treated them as complete human personalities where emotional dimensions hold equal importance. In this pap…

  2. arXiv cs.CL TIER_1 English(EN) · Xiaodong Gu ·

    HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?

    While LLM agents have demonstrated remarkable task-oriented abilities such as planning, reasoning, and action, few works have treated them as complete human personalities where emotional dimensions hold equal importance. In this paper, we introduce a novel benchmark to systematic…

RELATED ENTITIES

RELATED TOPICS