Yu Su
12 papers · 2063 citations
Most-cited papers
- Agentbench: Evaluating Llms As Agents2023 · 710 citations
- Mammoth: Building Math Generalist Models Through Hybrid Instruction Tuning2023 · 554 citations
- Travelplanner: A Benchmark For Real-world Planning With Language Agents2024 · 367 citations
- From RAG To Memory: Non-parametric Continual Learning For Large Language Models2025 · 125 citations
- Grokked Transformers Are Implicit Reasoners: A Mechanistic Journey To The Edge Of Generalization2024 · 80 citations
- One Step At A Time: Long-horizon Vision-and-language Navigation With Milestones2022 · 18 citations
- Agentbench: Evaluating Llms As Agents2023
- CUBE: A Standard For Unifying Agent Benchmarks2026
Topics