← Aojie (Justin) Yuan

Papers

Full text, abstracts, and BibTeX. Plain-language explainers live in Writing (中文).

• Findings of EMNLP 2026 · 2026

  WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

  Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang, Xiyang Hu, Yue Zhao, Shuli Jiang · PDF · arXiv

• Preprint · under review at ICLR 2027 · 2026

  CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering

  Prince Zizhuang Wang, Chenhao Liang, Zelong Xu, Aojie Yuan, Xiaolin Zhou, Haiyue Zhang, Yue Zhao, Xiyang Hu, Shuli Jiang · PDF · arXiv

• KnowFM @ ACL 2026 · ACM AI Summit 2026 (Visionary Papers) · 2026

  Auditable Agents

  Yi Nian, Aojie Yuan, Haiyue Zhang, Jiate Li, Li Li, Xiyang Hu, Hua Wei, Xiongye Xiao, Chaowei Xiao, Yue Zhao · PDF · arXiv

• NeurIPS 2026 (Evaluations & Datasets Track) · FAGEN @ ICML 2026 · 2026

  When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents

  Xiaolin Zhou, Aojie Yuan, Zheng Luo, Zipeng Ling, Xixiao Pan, Yicheng Gao, Haiyue Zhang, Jiate Li, Shuli Jiang, Prince Zizhuang Wang, Zixuan Zhu, Jinbo Liu, Ryan A. Rossi, Hua Wei, Xiyang Hu · PDF · arXiv

• AI4GOOD & FAGEN Workshops @ ICML 2026 · 2026

  SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

  Aojie Yuan, Yi Nian, Haiyue Zhang, Zijian Su, Yue Zhao · PDF · arXiv

• Preprint · 2026

  AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational Memory

  Aojie Yuan, Haiyue Zhang, Shahin Nazarian · PDF · arXiv

• Preprint · 2026

  Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning

  Aojie Yuan, Tianqi Shen, Dajun Zhang · PDF · arXiv

• Preprint (demo paper) · 2026

  Sovereign-OS: A Charter-Governed Operating System for Autonomous AI Agents with Verifiable Fiscal Discipline

  Aojie Yuan, Haiyue Zhang, Ziyi Wang, Yue Zhao · PDF · arXiv

• Mechanistic Interpretability Workshop @ ICML 2026 · 2026

  Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal

  Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang, Yi Nian, Yue Zhao · PDF · arXiv

• Preprint · 2026

  Beyond Language: Format-Agnostic Reasoning Subspaces in Large Language Models

  Aojie Yuan, Zhiyuan Su · PDF · arXiv

• Preprint · 2026

  Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of Readout

  Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang, Zijian Su · PDF · arXiv

• Preprint · 2026

  Jacobian Rank Collapse in Decision-Focused Learning

  Aojie Yuan, Haiyue Zhang, Zijian Su · PDF · arXiv

• Preprint · 2026

  HMAR: Hierarchical Modality-Aware Expert and Dynamic Routing Medical Image Retrieval Architecture

  Aojie Yuan · PDF · arXiv