I am a Master’s student in Electronic Information at the University of Science and Technology of China (USTC). I received my B.Eng. in Electronic Information Engineering from Hainan University. From May to November 2026, I was a Research Intern at Ant Group, advised by Yongqi Tong and Wei Wu.

My research focuses on self-evolving LLM agents, i.e., agents that keep improving from their own experience. Specifically, I work on:

  • Learning from experience without parameter updates: reflection, skill memory, and credit assignment for agents (REFLEX, NeurIPS 2026).
  • Failure diagnosis and recovery: diagnosing why agents fail and repairing them selectively (DARC, KDD 2027).
  • Agent skill acquisition at scale: mining verifiable, reusable skills from code (Code2Skill, Hugging Face Daily Papers #3).
  • Agent post-training: SFT, preference optimization, and RL (DPO / GRPO) for multimodal agents.

I also have prior experience in computer vision, including image restoration and object detection.

More on my Google Scholar.

🔥 News

  • 2026.11:  🎉🎉 Our paper DARC on selective self-correction for LLM agents is accepted to KDD 2027!
  • 2026.10:  🔥 PAR ranked #3 on Hugging Face Daily Papers!
  • 2026.09:  🔥 Code2Skill ranked #3 on Hugging Face Daily Papers!
  • 2026.09:  🎉🎉 Our paper REFLEX on self-evolving agents is accepted to NeurIPS 2026!
  • 2026.06:  🎉 CogSENet for blind image deblurring is accepted to ECCV 2026.
  • 2026.05:  📄 AtlasVA, teacher-free visual skill memory for VLM agents, is released on arXiv. Our RedNote post got 792 likes & stars!
  • 2026.05:  💼 Joined Ant Group as a Research Intern.
  • 2026.04:  🏆 Ranked 5th / 223 in the CVPR NTIRE 2026 Image Shadow Removal Challenge.

📝 Publications

* Equal contribution

2027

KDD 2027
DARC

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction

Pan Wang, Yihao Hu, Hang Wang, Zirui Lv, Xin Zhang, Jianshe Li, Jiang-Ming Yang, Wei Wu, Yongqi Tong

arXiv | CCF-A

  • A diagnose-before-recover paradigm (Profile → Diagnose → Evaluate → Distill → Freeze) that finds the dominant failure bottlenecks and triggers cost-aware self-correction only when the agent fails.
  • Cuts average environment steps by 54.2% and invalid actions by 92.9% on ALFWorld. It also generalizes to AppWorld and XBRL Finance.

2026

arXiv
PAR

PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

Pan Wang, Yihao Hu, Guangyuan Dong, Yitong Lin, Hang Wang, Zimi Liu, Zhihao Wen, Jianshe Li, Jiang-Ming Yang, Wei Wu, Yongqi Tong

arXiv | 🤗 Hugging Face Daily Papers #3

  • Makes extra recurrent depth in looped LMs useful for longer problems: iteration k is trained to match the state after the first k operations, and recurrent states are norm-anchored.
  • On swap-S5, a Qwen2.5-0.5B model trained on ≤32 moves reaches 95.5% full-state accuracy at 512 moves (16× the training length), versus 55.7% for RLT and 0.8% for explicit CoT.
arXiv
Code2Skill

Code2Skill: Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Yongqi Tong*, Pan Wang*, Hang Wang, Jianshe Li, Xin Zhang, Jiang-Ming Yang, Wei Wu

arXiv | 🤗 Hugging Face Daily Papers #3

  • Builds CodeSkillBank: 1,006,822 validated skills mined from 19,769 GitHub repositories.
  • Improves agents by 11.7% on average across 72 protocol-matched experiments, covering 9 model configurations and 8 benchmarks.
ECCV 2026
CogSENet

CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion

Pan Wang, Yihao Hu, Xiujin Liu

arXiv | Springer | CCF-B

  • An eagle-vision-inspired deblurring network. A Semantic-Driven State Space Module regroups tokens by semantics through differentiable routing, and a BiFreqFusionBlock separates high- and low-frequency features with wavelets.
  • A continuous Blur Field estimated from the blurry input is fused with CLIP semantic priors, so restoration adapts to spatially non-uniform blur.
NeurIPS 2026
REFLEX

REFLEX: Reflective Evolution from LLM Experience

Pan Wang

arXiv | CCF-A

  • A training-free self-evolving agent with a traceable Reflection–Generation–Memory–Credit Assignment loop. A vision-based Critic diagnoses failures, and a self-evolving Skill Memory accumulates, merges, and prunes reusable code skills.
  • Under a 100-call budget, it solves Acrobot, Pendulum, and Lunar Lander in a median of 13 / 20 / 24 calls, about half the calls of the baselines. It also cuts the invalid-program rate from 14.7% to 0.6%.
arXiv
AtlasVA

AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents

Pan Wang, Yihao Hu, Xiujin Liu, Jingchu Yang, Hang Wang, Zhihao Wen

arXiv | Project Page | 📕 RedNote (792 likes & stars)

  • Keeps VLM-agent memory visually grounded: a teacher-free, three-layer visual skill memory (spatial heatmaps, visual exemplars, and symbolic text skills) that evolves from trajectory statistics without any external LLM supervision.
  • Reuses self-evolving danger/affinity atlases as dense shaping rewards for RL. It outperforms text-centric memory baselines on Sokoban, FrozenLake, 3D embodied navigation, and 3D robotic manipulation.

2025

J. Agric. Food Res.
Multi-Strategy Framework

A Multi-Strategy Framework for Enhancing Shatian Pomelo Detection in Real-World Orchards

Pan Wang, Yihao Hu, Xiaodong Bai, Jingchu Yang, Leyi Zhou, Aiping Yang, Xiangxiang Li, Meiping Ding, Jianguo Yao

Journal of Agriculture and Food Research (JCR Q1, IF 7.2)

Paper | arXiv | Code

  • A multi-strategy framework for real orchards, which tackles device-dependent tone shifts, unstable lighting, large scale variation, and occlusion. It builds the multi-scenario STP-AgriData dataset and the REAS-Det detector with GSV-Conv.
  • Achieves 84.3% mAP@0.50 and 53.6% mAP@0.50:0.95 on STP-AgriData, outperforming recent detectors.
Smart Agric. Tech.
SDE-DET

SDE-DET: Precision Detection Network for Shatian Pomelos in Challenging Orchard Environments

Yihao Hu*, Pan Wang*, Xiaodong Bai, Shijie Cai, Hang Wang, Huazhong Liu, Aiping Yang, Xiangxiang Li, Meiping Ding, Hongyan Liu, Jianguo Yao

Smart Agricultural Technology (JCR Q1, IF 7.1)

Paper | arXiv | Code

  • A pomelo detector for complex orchards that combines Star Blocks, Deformable Attention for occlusion, and Efficient Multi-Scale Attention for small objects.
  • Reaches 0.838 mAP@0.5 (precision 0.883, F1 0.823), outperforming the YOLO series and other mainstream detectors.

Patents

  • An Interpretable Image-to-Text Description Method Based on Multi-Model Fusion, Invention Patent, CN202410750467.1, second inventor (supervisor listed first), Granted.

💻 Internships

  • 2026.05 - 2026.11, Research Intern, Ant Group, China. Advisors: Yongqi Tong and Wei Wu.
    • Million-scale agent skill synthesis: Contributed to the fully automated Code2Skill pipeline, which mined and validated 1,006,822 executable skills from 19,000+ GitHub repositories.
    • Failure diagnosis and repair for self-evolving agents: Led DARC, which diagnoses why agents fail and distills cost-aware recovery policies, so that agents can repair themselves and keep evolving. Accepted to KDD 2027.
    • Agent–environment co-evolution: Contributed to SEAL, a framework in which agents and their learning environments evolve together, to support scalable agent RL.
    • Multimodal agent post-training: Implemented SFT, preference optimization, Offline-DPO, and GRPO for long-horizon visual reasoning and tool use.

🎖 Honors and Awards

  • 2026 Excellence Award, UbiComp 2026 CUHK-X Multimodal Human Activity Challenge.
  • 2026 Rank 5 / 223, CVPR NTIRE 2026 Image Shadow Removal Challenge.
  • 2025 National Second Prize, China Robotics and Artificial Intelligence Competition.
  • 2024 National First Prize, National College Student Digital Media Technology Works and Creativity Competition.
  • 2024 National Second Prize, Global Campus Artificial Intelligence Algorithm Elite Competition.
  • 2024 National Third Prize, National College Student Information Security Competition.
  • 2024 National Third Prize, Lanqiao Cup National Software and Information Technology Competition.
  • 2023 National First Prize, Global Campus Artificial Intelligence Algorithm Elite Competition.
  • 2023 - 2025 National Undergraduate Innovation and Entrepreneurship Training Program: led 1 national-level project and participated in 2 others, all completed.

📖 Educations

  • 2026 - now, M.S. in Electronic Information, University of Science and Technology of China (USTC).
  • 2022 - 2026, B.Eng. in Electronic Information Engineering, Hainan University.