Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Coding Agents are Strong Prompt Optimizers
Agamdeep Singh, Srishti Gautam, Priyanshu Gupta +3
Search-based prompt optimizers improve prompts through iterative search: they propose edits, execute fresh rollouts, score the resulting trajectories, and retain only edits that im…
cs.AI2026
Back to the Future: A workbook time machine for spread sheet creation benchmarks
Mansi Uniyal, Agamdeep Singh, Ananya Singha +5
We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formul…