Get started
Author

Tao Gui

What is wrong with your code generated by large language models? An extensive study
2026 · Shihan Dou, Haoxiang Jia, et al. · Science China Information Sciences · 12
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
2026 · Zhiheng Xi, Chenyang Liao, et al. · International World Wide Web Conference (WWW) · 5
CL-bench: A Benchmark for Context Learning
2026 · Dou, Shihan, Zhang, Ming, et al. · arXiv (Cornell University) · 2
PDF
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
2026 · Lin, Jiahang, Liu, Shichun, et al. · arXiv (Cornell University) · 1
PDF
SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
2026 · Shen, Yujiong, Yang, Yajie, et al. · arXiv (Cornell University) · 1
PDF
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
2026 · Zhang, Ming, Tan, Kexin, et al. · arXiv (Cornell University) · 1
PDF
Uncertainty-Aware Sequence Labeling
2021 · Jiacheng Ye, Xiang Zhou, et al. · IEEE/ACM Transactions on Audio Speech and Language Processing · 1
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
2026 · Zhong, Jianyuan, Wu, Chenwei, et al. · arXiv (Cornell University)
PDF
QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering
2026 · Chen, Yujia, Wang, Yuhui, et al. · arXiv (Cornell University)
PDF
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
2026 · He, Hang, Wang, Linting, et al. · arXiv (Cornell University)
PDF
A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs
2026 · Kuang, Jiahao, Gao, Yangfan, et al. · arXiv (Cornell University)
PDF
EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning
2026 · Dou, Shihan, Liu, Shaofan, et al. · arXiv (Cornell University)
PDF
ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training
2026 · Zhang, Zhihao, Wu, Mingqi, et al. · arXiv (Cornell University)
PDF
Atria Dawn: The Dawn of Agentic Superintelligence
2026 · Guo, Honglin, Gui, Tao, et al. · arXiv (Cornell University)
PDF
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
2026 · Li, Jiaqiang, Yang, Yajie, et al. · arXiv (Cornell University)
PDF
NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment
2026 · Zhang, Guoqiang, Tan, Kexin, et al. · arXiv (Cornell University)
PDF
Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning
2026 · Zhao, Haoran, Du, Wei, et al. · arXiv (Cornell University)
PDF
Agents in the Large: Perception-Centered Architecture for Persistent Agents
2026 · Dou, Shihan, Jia, Haoxiang, et al. · arXiv (Cornell University)
PDF
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
2026 · Liu, Boyang, Jin, Senjie, et al. · arXiv (Cornell University)
PDF
MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques
2026 · Zhuang, Jiabao, Jiang, Changhao, et al. · arXiv (Cornell University)
PDF
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
2026 · Ye, Junjie, Sheng, Zhuohui, et al. · arXiv (Cornell University)
PDF
IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations
2026 · Zhu, Dingwei, Li, Jiahan, et al. · arXiv (Cornell University)
PDF
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
2026 · Xi, Zhiheng, Yang, Dingwen, et al. · arXiv (Cornell University)
PDF
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
2026 · Association for Computational Linguistics 2026, Chai, Mingxu, et al. · Underline Science Inc.
Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
2026 · Association for Computational Linguistics 2026, Cai, Xunliang, et al. · Underline Science Inc.
Works count: 60
Citation count: 23
H-index: 2
I10-index: 1
Year
Topic
Type