Awesome AI for Science
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Dakuo Wang — most-cited papers & profile · AI for Science
← authors
·
overview
Dakuo Wang
14
papers ·
0
citations ·
0
h-index
Northeastern University · Eastern University · Universidad del Noreste
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
2025
CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments
2026
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
2026
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
2026
Topics
Fine-Tuning
cs.CL
Model Architecture
Training Techniques
Prompting
Evaluation
Tool Use
Multi-Agent