Scholar
Weiwei Sun
Google Scholar ID: hdUZbxgAAAAJ
Carnegie Mellon University
Citations & Impact
Citations
1,472
H-index
17
i10-index
21
Publications
20
Co-authors
24
list available
Publications
Resume (English only)
Academic Achievements
- Training Proactive and Personalized LLM Agents (Preprint)
- Scaling Long-Horizon LLM Agent via Context-Folding (Preprint)
- Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management (Preprint)
- ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability (Preprint)
- CoMind: Towards Community-Driven Agents for Machine Learning Engineering (MTI-LLM@NeurIPS 2025)
- Enhancing Training Data Attribution with Representational Optimization (NeurIPS 2025 Spotlight)
- FrontierCO: A Comprehensive Evaluation of Contemporary ML-Based Solvers for Combinatorial Optimization (Preprint)
- CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization (Preprint)
- CodePDE: An Inference Framework for LLM-driven PDE Solver Generation (Preprint)
- ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval (Preprint)
- Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models (Preprint)
- Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning (NeurIPS 2025)
- MAIR: A Massive Benchmark for Evaluating Instructed Retrieval (EMNLP 2024)
- TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy (WWW 2025)
- MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter (ACL 2024)
- Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering (ACL 2024)
- Enhanced Generative Recommendation via Content and Collaboration Integration (CIKM 2024)
- Improving the Robustness of Large Language Models via Consistency Alignment (LREC-Coling 2024)
- How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study (Incomplete Title)
Research Experience
- Conducting PhD research at Carnegie Mellon University, involving multiple research projects on long-horizon LLM agents, scientific reasoning, and information retrieval.
Education
- PhD Student: Language Technologies Institute, Carnegie Mellon University, Advisor: Yiming Yang; M.E. and B.E.: Shandong University, Advisor: Zhaochun Ren.
Background
- Research Interests: LLM agents for long-horizon, scientific reasoning, information retrieval. Field: Natural Language Processing.
Miscellany
- Contact: Email, Twitter, LinkedIn, Google Scholar, GitHub
