DSGym: A Holistic Framework for Evaluating and Training Data Science Agents Paper • 2601.16344 • Published 4 days ago • 7
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning Paper • 2505.24273 • Published May 30, 2025 • 5
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks Paper • 2511.04662 • Published Nov 6, 2025 • 35
junlinw/opc-sft-s2-annealing-ins3-python-precode0.5-cb_AST_0.5_200.0_var3 Viewer • Updated Oct 6, 2025 • 2.24M • 31
junlinw/opc-sft-s2-annealing-ins3-python-precode0.5-cb_AST_0.0_200.0_var3 Viewer • Updated Oct 6, 2025 • 2.24M • 7
junlinw/opc-sft-s2-annealing-ins3-python-precode0.5-cb-og0.1entire_AST_0.5_200.0_var3 Viewer • Updated Oct 6, 2025 • 2.24M • 8
junlinw/opc-sft-s2-annealing-ins3-python-precode0.5-cb-og0.1entire_AST_0.0_200.0_var3 Viewer • Updated Oct 6, 2025 • 2.24M • 32
junlinw/opc-sft-s2-annealing-ins3-python-precode0.5-cb-og0.1entire_AST_1.0_200.0_var3 Viewer • Updated Oct 6, 2025 • 2.24M • 5