ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall Paper • 2510.07896 • Published Oct 9, 2025 • 11
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL Paper • 2605.18703 • Published May 18 • 50
FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence Paper • 2605.08820 • Published May 9 • 2
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration Paper • 2508.13755 • Published Aug 19, 2025 • 14
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR Paper • 2508.14029 • Published Aug 19, 2025 • 119