ConsumerSimBench evaluates 13 LLMs on reconstructing crowd reactions from 1,553 Chinese social-media topics using 23,122 auditable yes-no criteria, finding maximum coverage of 47.8% by Gemini-3.1-Pro.
Infusing Theory of Mind into Socially Intelligent LLM Agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Theory of Mind (ToM)-an understanding of the mental states of others-is a key aspect of human social intelligence, yet, chatbots and LLM-based social agents do not typically integrate it. In this work, we demonstrate that LLMs that explicitly use ToM get better at dialogue, achieving goals more effectively. After showing that simply prompting models to generate mental states between dialogue turns already provides significant benefit, we further introduce ToMAgent (ToMA), a ToM-focused dialogue agent. ToMA is trained by pairing ToM with dialogue lookahead to produce mental states that are maximally useful for achieving dialogue goals. Experiments on the Sotopia interactive social evaluation benchmark demonstrate the effectiveness of our method over a range of baselines. Comprehensive analysis shows that ToMA exhibits more strategic, goal-oriented reasoning behaviors, which enable long-horizon adaptation, while maintaining better relationships with their partners. Our results suggest a step forward in integrating ToM for building socially intelligent LLM agents.
years
2026 5representative citing papers
LLM robots match humans on engagement ratings in HRI questionnaires but systematically invert strangeness/comfort dimensions across models and live interactions.
Improvements in LLM Theory of Mind on static benchmarks do not reliably improve performance in dynamic, first-person human-AI interactions across goal-oriented and experience-oriented tasks.
An exploratory red-teaming study documents eleven cases of security, privacy, and governance failures in autonomous language-model agents with tool access and persistent memory.
Proposes an entropy-controlled pluralistic alignment framework with three modules to preserve strategic diversity and add verifiable audit trails in autonomous agent systems.
citing papers explorer
-
Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench
ConsumerSimBench evaluates 13 LLMs on reconstructing crowd reactions from 1,553 Chinese social-media topics using 23,122 auditable yes-no criteria, finding maximum coverage of 47.8% by Gemini-3.1-Pro.
-
When Robots Rate Their Own Interactions: Engagement Validity and the Strangeness Failure
LLM robots match humans on engagement ratings in HRI questionnaires but systematically invert strangeness/comfort dimensions across models and live interactions.
-
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
Improvements in LLM Theory of Mind on static benchmarks do not reliably improve performance in dynamic, first-person human-AI interactions across goal-oriented and experience-oriented tasks.
-
Agents of Chaos
An exploratory red-teaming study documents eleven cases of security, privacy, and governance failures in autonomous language-model agents with tool access and persistent memory.
-
Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents
Proposes an entropy-controlled pluralistic alignment framework with three modules to preserve strategic diversity and add verifiable audit trails in autonomous agent systems.