Running RL 1 Office Document Task Environment 📊 1 Step through a financial task environment with custom actions
view article Article Teaching LLMs to Play Carrom: A Physics-Based RL Environment for Frontier Agents 4 days ago • 1
view article Article Teaching LLMs to Play Carrom: A Physics-Based RL Environment for Frontier Agents 4 days ago • 1
Running RL 1 Office Document Task Environment 📊 1 Step through a financial task environment with custom actions
Running RL 1 Office Document Task Environment 📊 1 Step through a financial task environment with custom actions
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows Paper • 2512.13168 • Published Dec 15, 2025 • 53 • 5
bpHigh/gstar_assignment_2_prompt_modified_grpo_max_tokens_256_steps_120 2B • Updated Oct 12, 2025 • 1
bpHigh/gstar_assignment_2_prompt_modified_grpo_max_tokens_256_steps_120 2B • Updated Oct 12, 2025 • 1