InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants Paper • 2610.33966 • Published 2 days ago • 81
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published Jul 26 • 96
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning Paper • 2603.03790 • Published Mar 4 • 80