# UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.09215 · HTML: https://mlsanity.com/paper/2601.09215/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 24 of 24)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [Aligning Large Language Models with Human: A Survey](https://mlsanity.com/paper/2307.12966/) (2023)
- [UserRL: Training Interactive User-Centric Agent via Reinforcement Learning](https://mlsanity.com/paper/2509.19736/) (2025)
- [From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment](https://mlsanity.com/paper/2503.15463/) (2025)
- [Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2402.13374/) (2024)
- [Language Models that Think, Chat Better](https://mlsanity.com/paper/2509.20357/) (2025)
- [Goal Alignment in LLM-Based User Simulators for Conversational AI](https://mlsanity.com/paper/2507.20152/) (2025)
- [User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue](https://mlsanity.com/paper/2309.13233/) (2023)
- [User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation](https://mlsanity.com/paper/2501.04410/) (2025)
- [RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models](https://mlsanity.com/paper/2401.09432/) (2023)
- [VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series](https://mlsanity.com/paper/2510.21244/) (2025)

## Built on by (most cited first, 9 of 9)

- [Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors](https://mlsanity.com/paper/2605.07847/) (2026)
- [Unlocking Proactivity in Task-Oriented Dialogue](https://mlsanity.com/paper/2605.22240/) (2026)
- [EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents](https://mlsanity.com/paper/2605.27820/) (2026)
- [Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation](https://mlsanity.com/paper/2608.09420/) (2026)
- [Pretrained Persona Mixture Models and Tandem Models for Human Simulation](https://mlsanity.com/paper/2609.22607/) (2026)
- [TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation](https://mlsanity.com/paper/2609.28690/) (2026)
- [Proactive Dialogue Policy Optimization via Cognitive-State Transition](https://mlsanity.com/paper/2609.34948/) (2026)
- [MIMESIS: Learning User Simulators as Training Environments for Interactive Agents](https://mlsanity.com/paper/2610.09484/) (2026)
- [Training User Simulators with Latent Intrinsic Feedback](https://mlsanity.com/paper/2610.13617/) (2026)

## Abstract (arXiv)

User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods exhibit two issues. They rely on static and context-unaware profiles, necessitating extensive manual redesign for new scenarios, thus limiting generalizability. Moreover, they neglect human strategic thinking, leading to vulnerability to agent manipulation. To address these issues, we propose UserLM-R1, a novel user language model with reasoning capability. Specifically, we first construct comprehensive user profiles with both static roles and dynamic scenario-specific goals for adaptation to diverse scenarios. Then, we propose a goal-driven decision-making policy to generate high-quality rationales before producing responses, and further refine the reasoning and improve strategic capabilities with supervised fine-tuning and multi-reward reinforcement learning. Extensive experimental results demonstrate that UserLM-R1 outperforms competitive baselines, particularly on the more challenging adversarial set.