K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs Paper • 2605.09635 • Published 3 days ago • 53
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published 8 days ago • 134
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World Paper • 2607.17250 • Published 7 days ago • 88
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems Paper • 2606.22388 • Published Jun 21 • 95
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints Paper • 2606.05622 • Published Jun 4 • 44
Advancing Creative Physical Intelligence in Large Multimodal Models Paper • 2605.26396 • Published May 25 • 21
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 365