Author

Peng Xia

Observed name: Xia, Peng

Institutions: University of North Carolina at Chapel Hill, Google (United States), University of California, Santa Cruz, Beijing University of Technology

Observed institutions: University of North Carolina at Chapel Hill, Google (United States), University of California, Santa Cruz, Beijing University of Technology

OpenAlex ID: A5127035312

CoHARL: Co-Evolving Agent Policies and Executable Harnesses with Reinforcement Learning

2026 · Chen, Jianwen, Xia, Peng, et al. · arXiv (Cornell University)

PDF

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

2026 · Wu, Fang, Xing, Da, et al. · arXiv (Cornell University)

PDF

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

2026 · Xia, Peng, Han, Rujun, et al. · arXiv (Cornell University)

PDF

EnvHarness: Awakening Static Worlds for Agent Learning

2026 · Huang, Chengsong, Wang, Zifeng, et al. · arXiv (Cornell University)

PDF

Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization

2026 · Xia, Peng, Pang, Junbiao, et al. · arXiv (Cornell University)

PDF

Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models

2026 · Xia, Peng, Pang, Junbiao, et al. · arXiv (Cornell University)

PDF

VisualClaw: A Real-Time, Personalized Agent for the Physical World

2026 · Tu, Haoqin, Chen, Jianwen, et al. · arXiv (Cornell University)

PDF

MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution

2026 · Association for Computational Linguistics 2026, Azarang, Arian, et al. · Underline Science Inc.

SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read

2026 · Association for Computational Linguistics 2026, Han, Siwei, et al. · Underline Science Inc.

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

2026 · Liu, Jiaqi, Qiu, Shi, et al. · arXiv (Cornell University)

PDF

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

2026 · Liu, Jiaqi, Ye, Xinyu, et al. · arXiv (Cornell University)

PDF

AQES: enhancing post-training quantization robustness via statistical activation quantization error simulation

2026 · Peng Xia, Junbiao Pang · International Conference on Algorithms, Microchips, and Network Applications (AMNA)

ClawArena: Benchmarking AI Agents in Evolving Information Environments

2026 · Ji, Haonian, Xiong, Kaiwen, et al. · arXiv (Cornell University)

PDF

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

2026 · Liu, Jiaqi, Ling, Zipeng, et al. · arXiv (Cornell University)

PDF

AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

2026 · Su, Zhaochen, Gao, Jincheng, et al. · arXiv (Cornell University)

PDF

SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read

2026 · Peng, Yibo, Xia, Peng, et al. · arXiv (Cornell University)

PDF

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

2026 · Xia, Peng, Chen, Jianwen, et al. · arXiv (Cornell University)

PDF

MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution

2026 · Chen, Jianwen, Yang, Xinyu, et al. · arXiv (Cornell University)

PDF

Reliable and Responsible Foundation Models: A Comprehensive Survey

2026 · Yang, Xinyu, Han, Junlin, et al. · arXiv (Cornell University)

PDF

SimpleMem: Efficient Lifelong Memory for LLM Agents

2026 · Liu, Jiaqi, Su, Yaofeng, et al. · arXiv (Cornell University)

PDF

MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation

2025 · Tong, Haibo, Wang, Zhaoyang, et al. · arXiv (Cornell University)

PDF

Works count: 21

Citation count:

H-index:

I10-index: