Author

Wanxiang Che

Observed name: Che, Wanxiang

Institution: Harbin Institute of Technology

Observed institution: Harbin Institute of Technology

OpenAlex ID: A5124781919

When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement

2026 · Chen, Hao, Yan, Yukun, et al. · arXiv (Cornell University)

LexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation

2026 · Zhang, Wenbin, Li, ShangZhan, et al. · arXiv (Cornell University)

FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models

2026 · Wang, Dingzirui, Zhang, Xuanliang, et al. · arXiv (Cornell University)

CurateEvo: Data-Curation Evolving for Agentic Post-Training

2026 · Wang, Dingzirui, Zhang, Xuanliang, et al. · arXiv (Cornell University)

From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape

2026 · Chen, Hao, Han, Ziyu, et al. · arXiv (Cornell University)

HuoziIME: An On-Device LLM-Enhanced Input Method for Deep Personalization

2026 · Association for Computational Linguistics 2026, Che, Wanxiang, et al. · Underline Science Inc.

When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models

2026 · Association for Computational Linguistics 2026, Che, Wanxiang, et al. · Underline Science Inc.

Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards

2026 · Association for Computational Linguistics 2026, Che, Wanxiang, et al. · Underline Science Inc.

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models

2026 · Association for Computational Linguistics 2026, Che, Wanxiang, et al. · Underline Science Inc.

ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs

2026 · Association for Computational Linguistics 2026, Che, Wanxiang, et al. · Underline Science Inc.

Agent Exploration Toward Artificial General Intelligence

2026 · Ban, Yikun, Yang, Fengkai, et al. · Zenodo (CERN European Organization for Nuclear Research)

ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs

2026 · Xu, Yuzhuang, Han, Xu, et al. · arXiv (Cornell University)

When Does Context Help? Error Dynamics of Contextual Information in Large Language Models

2026 · Wang, Dingzirui, Zhang, Xuanliang, et al. · arXiv (Cornell University)

How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location

2026 · Zhang, Xuanliang, Wang, Dingzirui, et al. · arXiv (Cornell University)

CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

2026 · Luo, Xianzhen, Zhang, Jingyuan, et al. · arXiv (Cornell University)

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering

2026 · Guo, Chuanzhe, Wu, Jingjing, et al. · arXiv (Cornell University)

Large Language Model Agents Are Not Always Faithful Self-Evolvers

2026 · Zhao, Weixiang, Wang, Yingshuo, et al. · arXiv (Cornell University)

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

2026 · Chen, Qiguang, Du, Yantao, et al. · arXiv (Cornell University)

Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks

2026 · Association for Artificial Intelligence 2026, Che, Wanxiang, et al. · Underline Science Inc.

CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis

2026 · Association for Artificial Intelligence 2026, Che, Wanxiang, et al. · Underline Science Inc.

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction

2026 · Association for Artificial Intelligence 2026, Che, Wanxiang, et al. · Underline Science Inc.

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Significant Gains in Reasoning Efficiency in Large Language Models

2026 · Association for Artificial Intelligence 2026, Che, Wanxiang, et al. · Underline Science Inc.

Towards Generalizable Visually Grounded Exploration of Household Devices

2026 · Linhao Zheng, Zeming Liu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

LifeMem: Enabling Lifelong Experience Reuse for LLM Agents

2026 · Yuli Qiu, Yutong Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement

2025 · Zhao, Weixiang, Guo, Jiahe, et al. · arXiv (Cornell University)

Works count: 32

Citation count:

H-index:

I10-index: