Cover Image

The Era of Real-World Human Interaction: RL from User Conversations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Chuanyang, Xu, Jing, Liu, Bo, Tao, Leitian, Golovneva, Olga, Shu, Tianmin, Zhao, Wenting, Li, Xian, Weston, Jason
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Token Attention
by: Golovneva, Olga, et al.
Published: (2025)

Contextual Position Encoding: Learning to Count What's Important
by: Golovneva, Olga, et al.
Published: (2024)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
by: Xiong, Wei, et al.
Published: (2025)

Reverse Training to Nurse the Reversal Curse
by: Golovneva, Olga, et al.
Published: (2024)

SPICE: Self-Play In Corpus Environments Improves Reasoning
by: Liu, Bo, et al.
Published: (2025)

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
by: Yu, Zhaoning, et al.
Published: (2025)

R.I.P.: Better Models by Survival of the Fittest Prompts
by: Yu, Ping, et al.
Published: (2025)

The Majority is not always right: RL training for solution aggregation
by: Zhao, Wenting, et al.
Published: (2025)

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
by: Wu, Tianhao, et al.
Published: (2024)

AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
by: Zhang, Zhining, et al.
Published: (2025)

Your Weak LLM is Secretly a Strong Teacher for Alignment
by: Tao, Leitian, et al.
Published: (2024)

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
by: Tao, Leitian, et al.
Published: (2025)

CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
by: Yu, Ping, et al.
Published: (2025)

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users
by: Ye, Suyu, et al.
Published: (2025)

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
by: Tao, Leitian, et al.
Published: (2025)

Self-Improving Pretraining: using post-trained models to pretrain better models
by: Tan, Ellen Xiaoqing, et al.
Published: (2026)

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
by: Sukhbaatar, Sainbayar, et al.
Published: (2024)

Self-Taught Evaluators
by: Wang, Tianlu, et al.
Published: (2024)

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind
by: Shi, Haojun, et al.
Published: (2024)

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
by: Peng, Andi, et al.
Published: (2024)

Does the Appearance of Autonomous Conversational Robots Affect User Spoken Behaviors in Real-World Conference Interactions?
by: Pang, Zi Haur, et al.
Published: (2025)

Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss
by: Xu, Jing, et al.
Published: (2023)

Distilling System 2 into System 1
by: Yu, Ping, et al.
Published: (2024)

Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models
by: Nguyen, Thao, et al.
Published: (2025)

Can LLMs Infer Personality from Real World Conversations?
by: Zhu, Jianfeng, et al.
Published: (2025)

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
by: Wu, Junchao, et al.
Published: (2024)

MMToM-QA: Multimodal Theory of Mind Question Answering
by: Jin, Chuanyang, et al.
Published: (2024)

Self-Rewarding Language Models
by: Yuan, Weizhe, et al.
Published: (2024)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
by: Saha, Swarnadeep, et al.
Published: (2025)

Self-Challenging Language Model Agents
by: Zhou, Yifei, et al.
Published: (2025)

Enabling Real-Time Conversations with Minimal Training Costs
by: Xu, Wang, et al.
Published: (2024)

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
by: Qian, Cheng, et al.
Published: (2025)

$τ$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
by: Yao, Shunyu, et al.
Published: (2024)

Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations
by: Liu, Yu Lu, et al.
Published: (2026)

MindZero: Learning Online Mental Reasoning With Zero Annotations
by: Zhang, Shunchi, et al.
Published: (2026)

Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations
by: Singh, Bhaskar, et al.
Published: (2026)

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement
by: Tao, Leitian, et al.
Published: (2024)

AI-Powered Early Diagnosis of Mental Health Disorders from Real-World Clinical Conversations
by: Zhu, Jianfeng, et al.
Published: (2025)

PRISM of Opinions: A Persona-Reasoned Multimodal Framework for User-centric Conversational Stance Detection
by: Wang, Bingbing, et al.
Published: (2025)

Challenges and Future Directions of Data-Centric AI Alignment
by: Yeh, Min-Hsuan, et al.
Published: (2024)