MP
Maxm Pan
cs.AIcs.CLcs.LGcs.SE
On Valency
published · living versionsW_ckhskh27·v1 · currentpublished
TIDE: Tree-Induced Fine-Grained Diagnostic Evaluation from Model Behaviors
with Jiayi Chen, Hui Li, Yujiong Shen, Qiyuan Peng +10
1 version
Preprints & journals
13 papers in the corpus · 2026TIDE: Tree-Induced Fine-Grained Diagnostic Evaluation from Model Behaviors2610.29985v1 · Jiayi Chen, Hui Li, Yujiong Shen et al.2026 · 0 citationsarXivon Valency
REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing2609.36984v1 · Jiawen Tao, Xiaokun Yuan, Yaoming Li et al.2026 · 0 citationsarXiv
Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments2609.29773v2 · Yukai Wu, Yuanjing Yang, Le Zhou et al.2026 · 0 citationsarXiv
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds2609.30199v2 · Ming Zhang, Zhenghao Xiang, Peizhong Gao et al.2026 · 0 citationsarXiv
Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking2609.18909v2 · Xinshuai Guo, Junjie Wu, Dolly Deng et al.2026 · 0 citationsarXiv
WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective2609.15387v3 · Chenxu Liu, Zilu Zou, Peizhong Gao et al.2026 · 0 citationsarXiv
Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding2607.29196v2 · Eileen Ye, Jiawen Tao, Yaoming Li et al.2026 · 0 citationsarXiv
Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training2607.28109v2 · Jiawen Tao, Miao Peng, Yaoming Li et al.2026 · 0 citationsarXiv
E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios2607.23722v1 · Weihuang Zheng, Tianyuan Zou, Eileen Ye et al.2026 · 0 citationsarXiv
Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI2607.22368v1 · Jiaqi Shao, Hanck Chen, Wei Zhang et al.2026 · 0 citationsarXiv
AhaBench: Do Agents Turn Experience into Reusable Insights? A Long-Horizon Benchmark for Continual Learning2609.05435v2 · Zerui Cheng, Jiawei Xu, Huacan Chai et al.2026 · 0 citationsarXiv
HyperLogic: A Hard, Forward-Authored Chinese Logical Reasoning Benchmark with Execution-Derived Answers2605.19597v2 · Ming Zhang, Qiyuan Peng, Yinxi Wei et al.2026 · 0 citationsarXiv
TaxoBench: Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies2601.12369v6 · Ming Zhang, Jiabao Zhuang, Wenqing Jing et al.2026 · 0 citationsarXiv
Career total: 13 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.