Author

Maxm Pan

Observed name: Pan, Maxm

Institution: Tencent (China)

Observed institution: Tencent (China)

OpenAlex ID: A5143734700

REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing

2026 · Tao, Jiawen, Yuan, Xiaokun, et al. · arXiv (Cornell University)

PDF

Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments

2026 · Wu, Yukai, Yang, Yuanjing, et al. · arXiv (Cornell University)

PDF

ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds

2026 · Zhang, Ming, Xiang, Zhenghao, et al. · arXiv (Cornell University)

PDF

Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking

2026 · Guo, Xinshuai, Wu, Junjie, et al. · arXiv (Cornell University)

PDF

WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective

2026 · Liu, Chenxu, Zou, Zilu, et al. · arXiv (Cornell University)

PDF

Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding

2026 · Ye, Eileen, Tao, Jiawen, et al. · arXiv (Cornell University)

PDF

Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training

2026 · Tao, Jiawen, Peng, Miao, et al. · arXiv (Cornell University)

PDF

E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios

2026 · Zheng, Weihuang, Zou, Tianyuan, et al. · arXiv (Cornell University)

PDF

Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI

2026 · Shao, Jiaqi, Chen, Hanck, et al. · arXiv (Cornell University)

PDF

AhaBench: Do Agents Turn Experience into Reusable Insights? A Long-Horizon Benchmark for Continual Learning

2026 · Cheng, Zerui, Xu, Jiawei, et al. · arXiv (Cornell University)

PDF

HyperLogic: A Hard, Forward-Authored Chinese Logical Reasoning Benchmark with Execution-Derived Answers

2026 · Zhang, Ming, Peng, Qiyuan, et al. · arXiv (Cornell University)

PDF

TaxoBench: Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies

2026 · Zhang, Ming, Zhuang, Jiabao, et al. · arXiv (Cornell University)

PDF

TIDE: Tree-Induced Fine-Grained Diagnostic Evaluation from Model Behaviors

2026 · Jiayi Chen, Hui Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

AEGIS-D: Multi-Agent Debate for High-Precision Verification of Hard Competition Mathematics

2026 · Jiayang Sun, Jiawei Xu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

Works count: 14

Citation count:

H-index:

I10-index: