Wangchunshu Zhou
- Papers
- 49
Cite
Notes
Only stored in your browser.
Authored papers
49EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
arXiv 2026
Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
arXiv 2026
MemEvolve: Meta-Evolution of Agent Memory Systems
arXiv 2025
TaskCraft: Automated Generation of Agentic Tasks
arXiv 2025
A Comprehensive Survey on Long Context Language Modeling
arXiv 2025
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
arXiv 2025
OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
arXiv 2025
COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes
arXiv 2025
KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
arXiv 2025
ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
arXiv 2025
CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models
arXiv 2025
A Survey on Latent Reasoning
arXiv 2025
How Far Are We from Genuinely Useful Deep Research Agents?
arXiv 2025
Efficient Agents: Building Effective Agents While Reducing Cost
arXiv 2025
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
arXiv 2025
Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
arXiv 2025
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
arXiv 2025
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
arXiv 2025
A^2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
arXiv 2025
Reverse-Engineered Reasoning for Open-Ended Generation
arXiv 2025
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
arXiv 2025
M+: Extending MemoryLLM with Scalable Long-Term Memory
arXiv 2025
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values
arXiv 2025
Towards Personalized Deep Research: Benchmarks and Evaluations
arXiv 2025
Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
arXiv 2025
ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
arXiv 2025
Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures
arXiv 2025
VeriGUI: Verifiable Long-Chain GUI Dataset
arXiv 2025
Symbolic Learning Enables Self-Evolving Agents
arXiv 2024
MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
arXiv 2024
AI PERSONA: Towards Life-long Personalization of LLMs
arXiv 2024
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
arXiv 2024
AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
arXiv 2024
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
arXiv 2024
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
arXiv 2024
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
arXiv 2024
MIO: A Foundation Model on Multimodal Tokens
arXiv 2024
ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
arXiv 2023
RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text
arXiv 2023
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
arXiv 2023
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
arXiv 2023
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
arXiv 2023
Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?
arXiv 2023
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
arXiv 2023
Mixup Your Own Pairs
arXiv 2023
Evaluating Large Language Models on Controlled Generation Tasks
arXiv 2023
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
EMNLP 2021 11
BERT Loses Patience: Fast and Robust Inference with Early Exit
NeurIPS 2020 12
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
EMNLP 2020 11
Affiliations
Frequent co-authors
10from 49 papers