Papers by Diarmuid O Seaghdha
ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution (2025.acl-long)
Copied to clipboard
Alexandru Coca, Mark Gaynor, Zhenxing Zhang, Jianpeng Cheng, Bo-Hsiang Tseng, Peter Boothroyd, Hector Martinez Alonso, Diarmuid O Seaghdha, Anders Johannsen
| Challenge: | ASPERA framework allows developers to guide LLM generation of high-quality tasks based on user queries, simulation state and corresponding validation programs. |
| Approach: | They develop a framework comprising an assistant library simulation and a human-assisted LLM data generation engine to guide LLM generation of high-quality tasks . they use a dataset to evaluate 250 tasks generated using ASPERA . |
| Outcome: | The proposed framework can guide LLM generation of high-quality tasks tackling data availability and evaluation robustness challenges. |