Daniel Fried
12 papers · 913 citations
Most-cited papers
- Bigcodebench: Benchmarking Code Generation With Diverse Function Calls And Complex Instructions2024 · 471 citations
- Tree Search For Language Model Agents2024 · 134 citations
- Repetition Improves Language Model Embeddings2024 · 66 citations
- What Are Tools Anyway? A Survey From The Language Model Perspective2024 · 59 citations
- Hybrid-gym: Training Coding Agents To Generalize Across Tasks2026
- Propose, Solve, Verify: Self-play Through Formal Verification2025
- Odysseys: Benchmarking Web Agents On Realistic Long Horizon Tasks2026
- Agent Psychometrics: Task-level Performance Prediction In Agentic Coding Benchmarks2026
Topics