Copertina

Mind the Sim2Real Gap in User Simulation for Agentic Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Xuhui, Sun, Weiwei, Ma, Qianou, Xie, Yiqing, Liu, Jiarui, Du, Weihua, Welleck, Sean, Yang, Yiming, Neubig, Graham, Wu, Sherry Tongshuang, Sap, Maarten
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reinforcing Human Behavior Simulation via Verbal Feedback
di: Sun, Weiwei, et al.
Pubblicazione: (2026)

Training Proactive and Personalized LLM Agents
di: Sun, Weiwei, et al.
Pubblicazione: (2025)

Agentic-R1: Distilled Dual-Strategy Reasoning
di: Du, Weihua, et al.
Pubblicazione: (2025)

Optimizing Temperature for Language Models with Multi-Sample Inference
di: Du, Weihua, et al.
Pubblicazione: (2025)

TOM-SWE: User Mental Modeling For Software Engineering Agents
di: Zhou, Xuhui, et al.
Pubblicazione: (2025)

Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering
di: Vijayvargiya, Sanidhya, et al.
Pubblicazione: (2025)

Gym-Anything: Turn any Software into an Agent Environment
di: Aggarwal, Pranjal, et al.
Pubblicazione: (2026)

GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
di: Yang, Ningyuan, et al.
Pubblicazione: (2026)

Stereotype or Personalization? User Identity Biases Chatbot Recommendations
di: Kantharuban, Anjali, et al.
Pubblicazione: (2024)

Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective
di: Wang, Qiaosi, et al.
Pubblicazione: (2025)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
di: Vijayvargiya, Sanidhya, et al.
Pubblicazione: (2025)

Not Everyone Wins with LLMs: Behavioral Patterns and Pedagogical Implications for AI Literacy in Programmatic Data Science
di: Ma, Qianou, et al.
Pubblicazione: (2025)

Do LLMs exhibit human-like response biases? A case study in survey design
di: Tjuatja, Lindia, et al.
Pubblicazione: (2023)

Social World Models
di: Zhou, Xuhui, et al.
Pubblicazione: (2025)

SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning
di: Zhao, Chenyang, et al.
Pubblicazione: (2024)

How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging
di: Ma, Qianou, et al.
Pubblicazione: (2023)

SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
di: Fan, Xianzhe, et al.
Pubblicazione: (2025)

Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
di: Zhou, Xuhui, et al.
Pubblicazione: (2024)

BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
di: Li, Wenkai, et al.
Pubblicazione: (2024)

Inducing Programmatic Skills for Agentic Tasks
di: Wang, Zora Zhiruo, et al.
Pubblicazione: (2025)

SOTOPIA-TOM: Evaluating Information Management in Multi-Agent Interaction with Theory of Mind
di: YS, Yashwanth, et al.
Pubblicazione: (2026)

RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation
di: Zhu, Ming, et al.
Pubblicazione: (2026)

User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions
di: Fan, Xianzhe, et al.
Pubblicazione: (2024)

Mind the Sim-to-Real Gap & Think Like a Scientist
di: Parikh, Harsh, et al.
Pubblicazione: (2026)

RECAP: An End-to-End Platform for Capturing, Replaying, and Analyzing AI-Assisted Programming Interactions
di: He, Keyu, et al.
Pubblicazione: (2026)

From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
di: Welleck, Sean, et al.
Pubblicazione: (2024)

Better Synthetic Data by Retrieving and Transforming Existing Datasets
di: Gandhi, Saumya, et al.
Pubblicazione: (2024)

Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
di: Yerukola, Akhila, et al.
Pubblicazione: (2025)

Minion: A Technology Probe to Explore How Users Negotiate Harmful Value Conflicts with AI Companions
di: Fan, Xianzhe, et al.
Pubblicazione: (2024)

Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies
di: Cohen, Myke C., et al.
Pubblicazione: (2026)

1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning
di: Li, Wenkai, et al.
Pubblicazione: (2025)

GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses
di: Mun, Jimin, et al.
Pubblicazione: (2026)

What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use
di: Ma, Qianou, et al.
Pubblicazione: (2024)

SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation
di: Zhou, Xuhui, et al.
Pubblicazione: (2025)

Lean-STaR: Learning to Interleave Thinking and Proving
di: Lin, Haohan, et al.
Pubblicazione: (2024)

Quantification of Sim2Real Gap via Neural Simulation Gap Function
di: Sangeerth, P, et al.
Pubblicazione: (2025)

SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents
di: Wang, Ruiyi, et al.
Pubblicazione: (2024)

SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
di: Zhou, Xuhui, et al.
Pubblicazione: (2023)

Learning to Dock: A Simulation-based Study on Closing the Sim2Real Gap in Autonomous Underwater Docking
di: Chang, Kevin, et al.
Pubblicazione: (2025)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
di: Aggarwal, Pranjal, et al.
Pubblicazione: (2025)