Xuesong Yao
3 papers · 2025–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(11)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
large language model
(3)
benchmark evaluation
(2)
tool use
(2)
model generalization
(1)
reasoning evaluation
(1)
multi-hop reasoning
(1)
reasoning benchmark
(1)
reasoning capability
(1)
arithmetic reasoning
(1)
function calling
(1)
context compression
(1)
recitation behavior
(1)
reinforcement learning
(1)
multi-hop tool use
(1)
policy gradient
(1)
language model
(1)
Papers
Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression
ACL 2026
Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?
IJCNLP 2025
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
ACL 2025