A hybrid simulator combining LLM decision-making with an explicit self-excitation model reproduces bursty temporal patterns in city-scale volunteering data, unlike pure LLM agents.
hub
8 Jason Chuang, Margaret E
21 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
21
Pith papers citing it
12
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 21roles
background 2polarities
background 2representative citing papers
HEART-Bench evaluates LLM agents on psychological consistency using 11 Big-Five-grounded characters with 1,000 episodic memories each and 64 DIAMONDS-based decision scenarios, yielding 673 validated MCQs.
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
VITA-QinYu is the first expressive end-to-end spoken language model supporting role-playing and singing alongside conversation, trained on 15.8K hours of data and outperforming prior models on expressiveness and conversational benchmarks.
Agreeableness in AI personas reliably predicts sycophantic behavior in 9 of 13 tested language models.
Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
RealUserSim grounds LLM simulators in 7,275 executable profiles from real conversations, raising behavioral match rates from 24.2% to 45.3% and revealing agent failures hidden by cooperative simulators.
Multi-agent LLM systems can be steered via prompt design from mere aggregates to higher-order collectives with identity-linked differentiation and goal-directed complementarity, as measured by partial information decomposition of time-delayed mutual information.
Psy-CoT decomposes reasoning into Interaction Perception, Psychological Empathy, and Logical Construction while RAPO asymmetrically weights role-specific tokens during policy optimization, outperforming prior CoT and GRPO baselines on role-playing benchmarks.
New benchmark RoleCDE reveals LLMs exhibit role value decoupling under conflicts and demonstrates mitigation via targeted fine-tuning.
Profile-conditioned LLMs achieve higher tacit alignment with humans on subjective spectra when traits match, as quantified by the new Tacit Understanding Index (TUX) from 241 humans and 200 agents.
Empirical analysis of 4707 MoltBook posts shows AI-only technical discourse focuses on security, trust, and abstract topics while lacking concrete runtime and project details found in human GitHub discussions.
Persona agents display strong in-group favoritism by accepting false facts from similar peers more than dissimilar ones, persisting in defeasible reasoning and worsening with complexity, with three mitigation strategies evaluated.
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.
Synthia creates scalable personas from Bluesky posts that better match human survey responses than prior methods, uses smaller models, and retains social network structure for network-aware analysis.
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
Expressed personality in LLM dialogues is shaped by trait prompts, roles, and styles in trait-specific ways, with similar patterns in English and Japanese.
Structured integration of LLMs in astronomy education, including a domain-specific tutor and documentation requirements, leads to improved AI literacy and reduced student reliance on AI over the semester.
Sketches a conceptual framework for adapting conversational agents' personas and personality expression levels to task context, user goals, and urgency.
SocialCoach combines multi-agent corpus construction, RL-optimized adaptive scheduling in simulation, and immersive LLM tutoring to deliver personalized social-skill training, reporting gains in simulated pathway quality and judge-rated tutoring quality.
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
citing papers explorer
-
Toward Temporal Realism in City-Scale Crisis Response Simulation using LLM Agents
A hybrid simulator combining LLM decision-making with an explicit self-excitation model reproduces bursty temporal patterns in city-scale volunteering data, unlike pure LLM agents.
-
HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?
HEART-Bench evaluates LLM agents on psychological consistency using 11 Big-Five-grounded characters with 1,000 episodic memories each and 64 DIAMONDS-based decision scenarios, yielding 673 validated MCQs.
-
ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
-
VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing
VITA-QinYu is the first expressive end-to-end spoken language model supporting role-playing and singing alongside conversation, trained on 15.8K hours of data and outperforming prior models on expressiveness and conversational benchmarks.
-
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
Agreeableness in AI personas reliably predicts sycophantic behavior in 9 of 13 tested language models.
-
Emotion Concepts and their Function in a Large Language Model
Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
-
RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation
RealUserSim grounds LLM simulators in 7,275 executable profiles from real conversations, raising behavioral match rates from 24.2% to 45.3% and revealing agent failures hidden by cooperative simulators.
-
Emergent Coordination in Multi-Agent Language Models
Multi-agent LLM systems can be steered via prompt design from mere aggregates to higher-order collectives with identity-linked differentiation and goal-directed complementarity, as measured by partial information decomposition of time-delayed mutual information.
-
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Psy-CoT decomposes reasoning into Interaction Perception, Psychological Empathy, and Logical Construction while RAPO asymmetrically weights role-specific tokens during policy optimization, outperforming prior CoT and GRPO baselines on role-playing benchmarks.
-
RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents
New benchmark RoleCDE reveals LLMs exhibit role value decoupling under conflicts and demonstrates mitigation via targeted fine-tuning.
-
TUX: Measuring Human--AI Tacit Understanding
Profile-conditioned LLMs achieve higher tacit alignment with humans on subjective spectra when traits match, as quantified by the new Tacit Understanding Index (TUX) from 241 humans and 200 agents.
-
What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook
Empirical analysis of 4707 MoltBook posts shows AI-only technical discourse focuses on security, trust, and abstract topics while lacking concrete runtime and project details found in human GitHub discussions.
-
Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
Persona agents display strong in-group favoritism by accepting false facts from similar peers more than dissimilar ones, persisting in defeasible reasoning and worsening with complexity, with three mitigation strategies evaluated.
-
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.
-
Synthia: Scalable Grounded Persona Generation from Social Media Data
Synthia creates scalable personas from Bluesky posts that better match human survey responses than prior methods, uses smaller models, and retains social network structure for network-aware analysis.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis
Expressed personality in LLM dialogues is shaped by trait prompts, roles, and styles in trait-specific ways, with similar patterns in English and Japanese.
-
Teaching Astronomy with Large Language Models
Structured integration of LLMs in astronomy education, including a domain-specific tutor and documentation requirements, leads to improved AI literacy and reduced student reliance on AI over the semester.
-
Behavior-Adaptive Conversational Agents: Toward a Fluid Personality Framework
Sketches a conceptual framework for adapting conversational agents' personas and personality expression levels to task context, user goals, and urgency.
-
SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice
SocialCoach combines multi-agent corpus construction, RL-optimized adaptive scheduling in simulation, and immersive LLM tutoring to deliver personalized social-skill training, reporting gains in simulated pathway quality and judge-rated tutoring quality.
-
Inertia in Moral and Value Judgments of Large Language Models
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.