Elamur Research⌕
☰
home / authors / Xuesong Yao

Xuesong Yao

Xuesong Yao has 4 papers in our library, in 2025–2026, most of them on Language models & pretraining, Evaluation & benchmarks, Reasoning; often with Jiecao Chen, Yufei Xu, Zhengyin Du.

4 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 4 · 11 works · 83 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 21 times in our library · ⭐ Paper Stars ranking: #8663

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Tohoku UniversitySendai · Japan2025–2026 · 5 paperscurrent🎓Hong Kong Polytechnic UniversityHong Kong · China2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 4 worksComputer Science · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3 worksEvaluation & benchmarks · 1 workReasoning · 1 work

 Works by year

2020s

20262 papers20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025 · 15 citations)
    Benchmarks for LLM tool use rarely test true multi-hop behaviour. Most build datasets tool-first: they gather tools and then synthesize queries for them. Such tools often do not depend on one another, and answers cannot be checked reliably, so evaluation falls back on model-based judging, which carries bias. ToolHop…
  2. Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments (2026 · 6 citations)
    Training LLMs to call tools with reinforcement learning is difficult for two reasons. Online APIs make training environments unstable and costly to maintain, and judging trajectories usually requires a strong LLM as evaluator, which brings bias. The authors propose FTRL, which removes both problems. An automated…
  3. Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems? (2025 · 5 citations)
    The paper asks whether frontier LLMs actually reason through simple problems or mostly reproduce memorized solution templates.
  4. Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression (2026)
    Training LLM agents with reinforcement learning on long multi-turn tool-use tasks is limited by context growth.

 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

Venues

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

 Cited by

Papers of our library cite their works 21 times (of the 149,439 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated

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