DIDS: Domain Impact-aware Data Sampling for Large Language Model Training Paper • 2504.13227 • Published Apr 17, 2025
Measuring Hong Kong Massive Multi-Task Language Understanding Paper • 2505.02177 • Published May 4, 2025
LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning Paper • 2506.07443 • Published Jun 9, 2025
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving Paper • 2506.17104 • Published Jun 20, 2025 • 1
Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference Paper • 2509.08682 • Published Sep 10, 2025
R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification Paper • 2601.03715 • Published 3 days ago