Junxian He

Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification

SWE-RM: Execution-free Feedback for Software Engineering Agents

Internalizing World Models via Self-Play Finetuning for Agentic RL

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward

From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction

Non-myopic Generation of Language Models for Reasoning and Planning

Diving into Self-Evolving Training for Multimodal Reasoning

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

Diving into Self-Evolve Training for Multimodal Reasoning

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

From Scaling Law to Sub-Scaling Law: Understanding the Diminishing Returns of Larger Models

Math for AI: On the Generalization of Learning Mathematical Problem Solving

AdaptVis: Spatial Understanding in Vision-Language Models Requires Adaptive Attention