🧑‍🔬 Yang Wu

🏛️ Affiliations

🎓Worcester Polytechnic InstituteWorcester · United States2026 · 3 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving (2026 · 3 citations)
   Math benchmarks such as GSM8K and MATH test LLMs on clean, fully specified problems. Real engineering work is different: it involves physical context, missing information, competing goals and uncertainty. EngiBench is designed to measure how LLMs handle such tasks and to diagnose where they fail. Problems from many…
2. Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition (2026)
   The paper addresses a dilemma in using LLMs for sensitive work. Cloud-hosted models such as GPT-5 give strong answers, but sending them raw queries can reveal confidential research or legal intent. Purely local models keep data private but answer less well. The authors propose GTKA, a client-side, semantic-level…
3. From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams (2026)
   The paper addresses a weakness of proactive LLM agents that coordinate heterogeneous research teams. When they optimize only for immediate task accuracy, they keep sending work to the strongest member, typically the PI, while junior researchers stay idle. The authors call this the Individual-centric Trap. Their…
4. Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation (2026)
   LLM-based recommenders struggle with two problems. Collaborative signals (behavioral consensus from many users) are invisible to models that read only item text. Tool-using agents that could fetch such signals are too slow because each reasoning turn adds latency. The authors address both with a two-stage approach.…
5. “Excuse me, may I say something...” CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations (2026)
   Most LLM assistants for science are reactive: they speak only when asked. In a live research meeting, that means useful remarks may never be made. This paper presents CoLabScience, an assistant that follows biomedical team discussions as they unfold and decides on its own when to contribute and what to say.

🤝 Co-authors here

12 of 18 co-authors with a page, the most papers together first.

• Xiaozhong Liu ×3
• Rujing Yao ×2
• Yufei Shi ×2
• Zhuoren Jiang ×2
• Ang Li
• Haixu Tang
• Huan Yu
• Huan Zhao
• Jie Jiang
• Jingwei Xiong
• Jun Zhang
• Qian Li

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics ×4: Findings of the Association for Computational Linguistics 2026 ×4
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026

🔗 Cited by

Papers of our library cite their works 1 time (of the 149,439 papers whose bibliographies we read).

Updated 2 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/yang-wu/